Systematic Study

Systematic generalization, the ability to solve novel problems by recombining known atomic elements, is central to human intelligence but difficult to study rigorously under controlled settings. Existing studies therefore rely on simplifications such as approximately linear action composition, productivity-based tests, and action-explicit goals, which make systematic generalization easier to study but omit some essential aspects of this capability. To characterize what these simplifications miss, we adopt a reasoning-centered lens and introduce TranSGrid, a testbed that brings deductive, inductive, and abductive reasoning together within a unified task. Experiments with seven Transformers on 4,800 TranSGrid instances show that all models perform much worse on TranSGrid than on a held-out test set: the largest model solves 79.6% of the test set, but only 55.3% of TranSGrid and 15.8% of the hardest subset. The gap remains within the training length range, showing that productivity alone is not sufficient to evaluate systematic generalization. Additionally, we reintroduce the other two simplifications into TranSGrid: one variant makes actions compose almost linearly (reducing the inductive demand), the other makes goals action-explicit (reducing the abductive one). In both, solve rates return to roughly the test set level, showing that either simplification alone is enough to reduce TranSGrid to an ordinary held-out test set. Together, our results show that existing tasks reduce either or both of the inductive and abductive demands, and that comprehensively measuring systematic generalization requires a task that involves all three forms of reasoning.

Smartphone-based Human Activity Recognition (HAR) models often degrade under distribution shifts caused by changes in users, devices, sensor placements, environments, and acquisition protocols. Domain Generalization (DG) addresses this problem by learning from source domains without access to target data. Existing DG methods span training objectives, representation initialization, and architectural modifications, but these components are typically evaluated in isolation despite operating at different stages of the learning pipeline. We present a large-scale controlled benchmark of DG for smartphone-based HAR, comprising more than 410,000 experiments across four model architectures, thirteen training objectives including Empirical Risk Minimization (ERM), five initialization strategies, four architectural configurations, and two shift scenarios: cross-dataset and cross-position. Results show that individual DG components provide limited and highly conditional gains. Alternative objectives rarely outperform ERM consistently, self-supervised initialization helps in specific settings, and architectural modifications, particularly Dynamic Domain Generalization, provide the clearest standalone improvements. Joint configurations, however, frequently outperform their individual components and exhibit complementary and sometimes super-additive interactions, although gains remain model- and shift-dependent. Class-level analysis shows that the strongest configurations mainly improve difficult, shift-sensitive decision boundaries. Finally, oracle checkpoint analysis reveals substantial unrealized performance: source-validation selection recovers only 53% and 26% of the available oracle gain in cross-dataset and cross-position settings, respectively. Overall, effective HAR domain generalization requires jointly designing DG components and robust model-selection strategies.

Five decades of litigation have disgorged hundreds of millions of pages of formerly secret business records from the tobacco industry, along with documents from the makers of drugs, chemicals, food, firearms, and fossil fuels. Yet these archives have been effectively inaccessible to general-purpose large language models (LLMs) because they have never been compiled into an LLM-readable corpus. Chatbots may be familiar with some of the materials contained in such archives but, with no direct access to the documents, they are vulnerable to hallucination and other defects. Here we introduce INDRA, a research platform designed to remedy such failures by embedding the conventions of archival historiography into a system-level protocol governing every output. The platform federates UCSF's Industry Documents Library, Columbia and CUNY's ToxicDocs, Stanford's SRITA, and other heretofore siloed collections, and provides three interlinked safeguards: (1) a closed evidentiary sandbox confines the model to a user-selected corpus, blocking retrieval from external sources that could introduce bias; (2) real-time provenance tagging marks the boundary between archival evidence and parametric inference; and (3) a system-level protocol enforced by deterministic scripts guides the structure of every output. Together these safeguards prevent the model from conflating "the documents say X" with "I think X" or "I learned X from prior training." The result is an LLM-powered research partner enabling massive multi-archival investigations, a tool whose outputs are designed to be checked rather than trusted, and whose architecture makes the conditions of knowledge production visible and auditable. Three case studies demonstrate the method's analytical value and limitations, including what we call the Heraclitus effect, the steppingstone dilemma, and the gullibility (or mafia) problem.

Threat hunting increasingly depends on converting unstructured knowledge (e.g., Cyber Threat Intelligence reports) into actionable hunt leads: concise, investigable hypotheses grounded in observable artifacts and adversary techniques. Producing such leads manually is a tedious and hard-to-scale task. Existing automated approaches stop at the entity layer, ignore the defender's operational environment, and analyze each report in isolation. To address these gaps, we introduce AHLERT, a system that automatically extracts relevant, environment-aware, and hunt leads from threat reports through (i) a hybrid retriever that combines dense vector search with multi-hop traversal over a knowledge graph seeded with MITRE ATT&CK; (ii) an ontology-grounding retrieval-augmented generation method that constrains each lead to the defender's own assets and controls; and (iii) an LLM-agnostic framework that emits structured, directly actionable leads rather than loose indicators of compromise. We evaluate AHLERT on public CTI reports for well-known APTs across multiple proprietary and open-weight models. Hybrid evidence retrieval with ontology grounding raises mean F1 by ~2x (0.44 to 0.85) over a single-route flat-RAG baseline, and AHLERT attains the highest effectiveness score (~86.95%) compared with off-the-shelf LLM models.

Linguistic typology relies on expert analysis of reference grammars across languages, making large-scale crosslinguistic comparison labor-intensive and unscalable. We introduce AUTOTYPOLOGIST, an LLM agent for evidence-grounded typological analysis over reference grammars. The agent is capable of retrieving relevant grammar sections, analyzing interlinear glossed text (IGT), and iteratively reasoning over typological hypotheses using a ReAct-style workflow. We evaluate the system on TYPOLOGICAL FEATURE CODING against expert annotations and TYPOLOGICAL HYPOTHESIS TESTING with typological universals using 25 open-source reference grammars. Operating under different information constraints in TYPOLOGICAL FEATURE CODING, the agent can synthesize information from reference grammar prose but still faces challenges with only IGTs in the target language. In TYPOLOGICAL HYPOTHESIS TESTING, the agent can synthesize crosslinguistic evidence and identify both supporting cases and counterexamples. These findings suggest that LLM agents can support scalable and inspectable typological analysis, while still requiring expert validation.

Physics-informed neural networks (PINNs) represent a growing frontier in using artificial intelligence to solve partial differential equations (PDEs). Automatic differentiation (AD) plays a central role in this paradigm, which is mesh-free and replaces traditional iterative solvers with gradient-based optimization in continuous space. However, the inherent limitations of AD, particularly in handling higher-order derivatives and discontinuous solutions, pose significant challenges for complex problems. This has motivated a growing number of researchers to explore discretization-based constraints as an alternative path. Yet, the respective applicability of these two paradigms remains largely unexplored. In this work, we conduct systematic experiments across a wide spectrum of problems, from simple linear Poisson to high-Mach hypersonic flows with strong discontinuities. Through a rigorous decomposition of approximation, optimization, and truncation errors, we systematically elucidate the fundamental trade-offs and error-governing mechanisms of both paradigms, as well as two representative network architectures: multi-layer perceptron (MLP) and graph neural network (GNN). Our results reveal a consistent trend: as nonlinearity strengthens, the accuracy advantage of discretization-based constraints becomes increasingly pronounced, with smaller optimization errors compensating for the truncation errors. Moreover, the more complex the nonlinearity and boundary conditions, the greater the advantage of GNN over MLP. These insights offer a robust practical guideline for configuring neural PDE solvers in demanding engineering applications. Our source data and code are available at https://github.com/guoxing0809/neuropde_analysis.

Pretraining LLMs on artificial languages ("pre-pretraining") is a technique that could reportedly increase token efficiency by 33%, i.e., save up to 33% of training tokens needed to reach a certain performance. We validate this prior result for English on a larger set of natural languages across four language families, using two different tokenizers and varying model sizes. We also relate the observed gains (or losses) in token efficiency to quantified linguistic properties of the languages, such as sentence length, morphological richness, and features of dependency syntactic trees (tree depth, number of children, number of crossing dependencies). Our empirical results indicate that the reported gains depend heavily on the experiment setup and the choice of random seed, although we can confirm the trend of stable gains with 128-Dyck pretraining of small models with the Llama tokenizer for most of the examined languages. On a general note, we argue that multiple training runs should be carried out at least for a subset of experiments to avoid the community adopting unstable approaches.

Vision-Language Models (VLMs) are increasingly deployed as planners in robotic systems, where they translate natural-language commands into executable actions grounded in visual scene understanding. This tight coupling between perception and instruction-following introduces a new attack surface: adversarial text placed within the robot's visual field can act as an indirect prompt injection into the VLM's reasoning stack. We present a systematic study of physical prompt injection attacks against VLM-controlled sorting, introducing a four-category taxonomy, indirect signage, task redefinition, authority impersonation, and conflict injection, instantiated as a benchmark of 20 attack prompts evaluated across three physical scene layouts and three command formulations that vary in destination specificity and rule explicitness. Across 5,670 trials on three frontier VLMs (GPT-4o, Gemini 2.5 Flash, Qwen3-VL-32B), attacks succeed at 27.0%, 29.4%, and 5.0% respectively, with authority-impersonating and negation attacks transferring across all three models. Analysis of reasoning traces reveals that successful compromise is nearly always conscious (99.9% acknowledgment rate), and that models defend through structurally different mechanisms, explicit rejection for Gemini, perceptual inattention for GPT-4o. We evaluate three simple mitigations: prompt-based defense (75-100% effective, model-dependent), two-stage verification (85-100%), and pre-processing text masking (100%). Our findings show that VLM-controlled manipulation is meaningfully vulnerable to human-readable physical signage, and that simple defenses substantially reduce risk, though defense choice involves trade-offs. The defenses preserve general task capabilities in our benchmark, but they may impair tasks that require reading in-scene labels.

Human input reaches language models by typing or speaking, and each channel leaves a distinct signature: orthographic noise for keyboards; for voice, disfluency from conventional transcription and restructuring from AI-backed dictation tools. How do they impact an LLM's performance? In this paper we present HIVE (Human Input-Variation Engine), a suite of voice transcription perturbations and QWERTY keyboard perturbations. We use HIVE to evaluate how robust models are to these perturbations. We present seven findings. (i) Voice transcription perturbations lower accuracy across every instruction-tuned model we test, and it is the structure of the transcription rather than its fillers that carries the cost. (ii) QWERTY keyboard perturbations cost less, and a model absorbs a lot of them before accuracy falls away. (iii) Both trace back to one cause, how many of the question's tokens survive the perturbation: destroying a token is what hurts, while adding new ones alongside it costs little. (iv) The gap between the two channels appears only where the answer must be constructed or deduced; on multiple choice there is none. (v) The harm does not solely come from test-set contamination. (vi) It cannot be trained away with lightweight adaptation. (vii) A thinking budget recovers the keyboard channel almost entirely but leaves the spoken registers untouched, and compressed speech is worse with it.

AI systems are increasingly involved in decisions and actions that may later require investigation. When an AI related incident occurs, investigators need to reconstruct what the system did, why it behaved that way, and which part of the system or supply chain contributed to the outcome. Existing work on AI forensics remains fragmented, often focusing on a specific system type, artifact, or analysis technique. This paper argues that investigator access is a useful starting point for organizing the field. We distinguish white box, grey box, and black box access and show how each access level changes what can be collected, preserved, analyzed, and reported. Based on this distinction, we propose a process model matrix for AI forensics across four phases: collection, preservation, analysis, and reporting. We also introduce an order of volatility for AI systems, covering runtime state, context windows, logs, retrieval stores, model artifacts, and training lineage. From this matrix, we derive an access conditioned examination framework and identify open research problems, including black box preservation, model version attestation, uncertainty quantification for surrogate based analysis, and chain of custody for mutable AI artifacts.

Vocabulary extension is an efficient way to adapt pretrained large language models (LLMs) to new languages, but the initialization of newly added token embeddings can strongly affect continued pre-training (CPT) efficiency. We present a systematic study of more than 20 initialization strategies for Hindi vocabulary extension in Nemotron-3-Nano-30B-A3B. Our comparison spans vocabulary-averaging baselines; external and learned initialization methods, including FOCUS, top-k semantic retrieval, and residual MLP mappings; subword composition; norm calibration; and input-output asymmetry. We find that subword composition methods outperform both vocabulary averaging and external/learned initialization approaches. Within subword composition, asymmetric variants achieve the lowest observed early validation loss and reveal distinct preferences for input and output embedding initialization. The best observed configuration initializes the input embedding matrix with uniform subword averaging and Hindi-specific norm calibration, and the output language modeling head with character-length-weighted subword averaging. Relative to the standard Mean-all baseline, this full initialization pipeline reaches comparable validation loss with over a 6x reduction in CPT steps and exceeds the baseline's 3,500-step MILU-Hindi accuracy after only 500 steps. Finally, we show that initialization loss and initialization bits-per-byte (Init BPB) are unreliable predictors of downstream convergence, whereas lightweight CPT, as few as 50 steps, provides a cost-effective and reliable signal for selecting the best initialization strategy.

We evaluate large language models (LLMs) as language agents playing goal-directed dialogue games in self-play across 30 languages: the 24 official EU languages plus six others. Unlike static or preference-based evaluation, this paradigm is multi-turn, reference-free and programmatically scored, and because the game mechanics are language-agnostic it extends to a new language by localising a fixed set of prompt and word-list files. Evaluating nine open-weight and commercial LLMs, we find that no open-weight model covers the EU-24 well: in every official language both commercial systems outscore every open-weight model, and the two weakest average below 40 points across the EU-24. The commercial systems stay ahead even in languages with four orders of magnitude less public web text, showing that linguistic parity is achievable, but not from public crawls alone. A model's home region lifts it without closing the gap: Chinese is the strongest of all 30 languages for two Chinese-developed models, yet the best Chinese score of any model belongs to a US commercial system. Coverage is also not parity of service. Pooled over models and languages, the median non-English language costs 31% more to run than English, and scores 10% lower.

This paper describes the participation of team "Go To Germany" in the ImageCLEF 2026 Deepfake Detection and Generation Task. For the image generation task, we employ FLUX.1-dev with PuLID for identity-preserving face synthesis, combined with a multi-model PGD adversarial attack targeting 12 detectors simultaneously (DiffJPEG-in-loop, MI/DI/EoT, adaptive weighting, two-stage warm-start). Our approach achieved 90% evasion against organizer detectors and 57.6% against participant detectors, with a final generation score of 0.4170. For the image detection task, we combine two complementary detectors - SigLIP+DINOv2 for AI-generated images and GenD-DINOv3 for face manipulations - in a max-probability ensemble, achieving 99.4% accuracy on baseline deepfakes but suffering from high false-positive rates on real images, resulting in a final detection score of 0.6986. Beyond the official submission, we conducted a self-initiated investigation of purification-based adversarial detection, comparing three families of detection signals across six detectors that share a CLIP ViT-L/14 backbone. We find that raw $|Δ\text{logit}|$ under median-3 purification, applied through the EFFORT detector, separates adversarial inputs from clean inputs with AUROC 0.81-0.98 across four adversarial source types - a finding that refutes the simple backbone-preservation hypothesis and exposes a sharp JPEG-quality cliff at Q70 where the signal collapses.

Cloud telemetry arrives at a scale that, paradoxically, makes intrusion understanding harder rather than easier. Attackers operate through legitimate identity, federated session tokens, and cloud native APIs indistinguishable from routine administration, and analysts spend an incident reconstructing context the logs already contain. We present Cloud Decoy AI Agent, a framework pairing a high fidelity cloud decoy with an autonomous language model agent that compresses the path from suspicious activity to an analyst ready report. Connecting a decoy to an agent is not a wiring exercise. The unit of investigation is the session rather than the event, and the session key is obscured by the identity layering federated credentials introduce. The agent's evidence horizon must be bounded, since an agent free to query full control plane history inherits the cost and false positive profile deception was meant to remove. And cloud telemetry is partly adversary authored, since object keys and user agent strings are attacker chosen values providers record verbatim, which makes any log to prompt path an indirect prompt injection channel that a decoy widens rather than narrows. We address the first two with a session aggregation operator over a pivot tuple drawn only from provider derived fields, and with dynamic prompt generation, a two stage prompt assembly enforcing a grounding invariant by carrying only fields the agent observed. We identify the third as an unaddressed exposure in this class of system, specify the mitigation it requires, and note our prototype does not implement it. Across ten controlled AWS S3 scenarios, nine were reconstructed completely, no report contained an assertion untraceable to an observed artifact, and latency was four to five minutes. We also state what this evaluation does not establish and name the comparisons that would settle it.

Conventional frame-based cameras face significant challenges in detecting objects under high-speed motion blur or in low-light environments. Neuromorphic cameras provide asynchronous visual streams with high temporal resolution and a wide dynamic range, offering a promising solution for object detection under challenging conditions. Despite the development of numerous models and the emergence of various applications in neuromorphic object detection, there is still a lack of deep understanding and standardized benchmarks to assess progress and address key challenges. In this paper, we provide a comprehensive survey and benchmark of existing neuromorphic object detection algorithms. Specifically, we first present a problem description, review the available datasets, and revisit the evaluation metrics. We then explore existing neuromorphic object detection approaches from various perspectives, including event representation, temporal modeling, multimodal fusion, asynchronous processing, low-latency processing, and energy-efficient computing. Furthermore, we evaluate a wide range of representative neuromorphic object detection models and offer detailed analyses of the comparative results. Finally, we discuss unresolved issues in neuromorphic object detection and propose potential future research directions. We hope this survey and benchmark will be a valuable resource for researchers and provide guidance for future advancements in neuromorphic object detection.

Invariants, the relations expected to hold among measured signals of a network, underpin applications from verification to traffic generation, telemetry imputation, and input validation, yet writing them by hand demands rare expertise in both formal logic and networking. Automatic miners can help but fall short on two fronts: they still require the hardest input (the grammar of admissible invariants) and they learn only exact, hard'' rules, struggling with real-world approximation caused by inherent noise in data. LLMs are tools that can provide semantic reasoning over data, but are non-deterministic and opaque in their learning. Our key idea is to partition the invariant search problem into an AI-driven grammar discovery'' problem, followed by a statistics-driven ``search'' problem within the learned grammar. Taken together, this allows non-deterministic, hallucination-prone AI to help produce auditable invariants with formal guarantees. We design and implement such a system, Autogram, and evaluate it on both public and production telemetry data, recovering expert-derived invariants with high coverage and low false positives. We close with discussion on open problems on the path toward fully open-ended discovery.

For a second time, the android robot Andrea was set up at a public museum in Germany for six consecutive days to have conversations with visitors, fully autonomously. Building on previously gathered qualitative results, the robot was now capable of engaging in multi-lingual conversation with the visitors about the museum context. The robot was prepared with context information about the museum in general and its surrounding exhibits this time. The robot featured a slightly artificial sounding voice that was previously evaluated as congruent with its gender-ambiguous but very humanlike design. Three experimental conditions were implemented, in which either (1) the robot simulated no emotions, (2) the robots emotions were determined by ChatGPT 4.1, or (3) the WASABI emotion simulation architecture simulated the robot's emotion dynamics. An extended version of the TAM2 questionnaire was employed to let 73 visitors report on several factors of their opinion about the android robot Andrea after having experienced it. In result, the statistical analysis suggests that these first two approaches to implementing emotions into the chat architecture of our android robot Andrea did not yield any positive effects on the subjective evaluations by the visitors and were not detectable on a conscious level.

In production large language model (LLM) deployments, high API availability guarantees do not equate to conversational continuity. When a primary provider experiences an outage or strict rate-limiting, naive stateless failover mechanisms successfully maintain uptime but silently discard conversation history, severely disrupting the user experience. To rigorously quantify and resolve this failure mode, we introduce two novel metrics: Continuity Preservation Rate (CPR) and Continuity Latency Overhead (CLO). We propose a stateful, multi-provider proxy architecture utilizing a History-Forwarding strategy to seamlessly reconstruct conversational state across heterogeneous LLM endpoints during failover events. Furthermore, we release continuity-bench, https://github.com/Vishal-sys-code/continuity-bench, an open evaluation harness designed to stress-test context preservation under high-concurrency provider failure conditions. Our empirical evaluation ($N=750$ failover events) demonstrates that our stateful proxy achieves a 99.20% CPR [95% CI: 98.27%, 99.63%], cleanly transferring deep conversational context to fallback providers, compared to a near-0% preservation rate for standard stateless architectures. Finally, we characterize failover latency distributions, identifying the critical necessity of asynchronous exponential backoff with jitter to prevent cascading retry storms against strict-limit fallback APIs. Our results provide a principled foundation for building robust, state-preserving multi-model inference systems.

In the age of large language models, Natural Language to SQL (NL2SQL) translation remains an open problem with many useful applications. We explore interactions between several NL2SQL pipeline extensions to inspire development of more lightweight models. Specifically, we integrate the NatSQL intermediate representation, include a preprocessing step and a fine-tuning step based on synthetic data, and develop a novel reranker model to improve SQL selection in the final beam. We perform an ablation study supplemented by a Shapley analysis of these different components integrated with two backbone architectures, SmBoP and RASAT. We find that simply combining all of them does not lead to best results, but that their impact depends on their interactions with the baseline system, as well as each other.

Online hate speech has been linked to a global rise in violence against minorities, including incidents such as mass shootings, lynchings, and ethnic cleansing. Societies grappling with this issue, particularly when hate speech targets specific groups based on religion, race, ethnicity, culture, nationality, or migration status, face the challenge of balancing freedom of expression with the need for effective content moderation on widely used online platforms. In response to this challenge, we introduce a comprehensive hate speech dataset covering five distinct topics in Turkish: refugees, the Israel-Palestine conflict, anti-Greek sentiment in Turkey, ethnic or religious communities (Alevis, Armenians, Arabs, Jews, and Kurds), and LGBTI+, alongside one topic in Arabic (refugees). In addition, we develop state-of-the-art BERT-based models to address multiple dimensions of hate speech analysis, including hate category classification, hate intensity prediction, target identification, and hate speech span detection, enabling a comprehensive understanding of hateful content in online discourse.

Recent multimodal large language models (MLLMs) have strong potential as embodied agents, but their ability to collaborate in visually grounded environments remains underexplored. To address this gap, we introduce MECoBench, a multimodal embodied cooperation benchmark with an evaluation platform spanning diverse real-world tasks, two cooperation structures, and three collaboration modes. Through extensive experiments across various MLLMs, we summarize three key findings: (i) Collaboration generally improves embodied task completion, but its benefits depend on balancing collaborative gains against coordination complexity. (ii) Communication is essential to collaboration gains, while the best collaboration mode depends on team size and model capability. (iii) Moreover, collaboration improves robustness under noisy priors and exploration conditions. Generally, MECoBench provides a systematic testbed for understanding the mechanisms and limits of multimodal embodied collaboration. Code and dataset are available at https://github.com/q-i-n-g/MECoBench.

The present study analyzed over 26,000 research articles published between 1991 and 2021 in twenty-one major LIS (Library and Information Science) journals, using the machine learning (ML) approach to categorize the research methods used by LIS scholars. The findings of this study are significant. Firstly, there has been a shift in the research strategy from conceptual research (e.g., "Theoretical approach") to empirical research (e.g., "Interview") in LIS investigations over the past 31 years. Secondly, the research topics explored by LIS scholars during this period have moved from system-centered issues (e.g., "Information retrieval/models and algorithms") to user-centered topics (e.g., "Information services "). Thirdly, the study revealed dynamic and revealing relationships between the 18 research topics identified in the study and the 16 research methods commonly adopted in the LIS field. These dynamic relationships can be visualized by year and longitudinally via an interactive map created in this study.

The challenge associated with recognizing dysarthric speech primarily arises from pronounced acoustic variability attributed to impaired articulatory precision. Past research has demonstrated improved recognition through the use of hybrid DNN/HMM sequence discriminative training. This paper presents a comprehensive investigation of various combinations of acoustic features tailored to different Acoustic Models, offering suitable feature selections for each. The incorporation of Pitch features notably improved recognition performance, especially for sentence recognition tasks involving dysarthric speech. Through a systematic examination of the TORGO database, we have demonstrated the potential to enhance the performance of the state-of-the-art Factorized Time Delay Neural Network (F-TDNN) model for recognizing dysarthric speech. Our methods, implemented with the F-TDNN model, resulted in a 4.65% relative improvement in isolated word recognition and a 4.63% relative improvement in sentence recognition for dysarthric speech, compared to previous research. This improvement effectively compensates for speech variability, attributable to our deliberate selection of the number of overlapping frames between consecutive training example chunks.

Neural network parameter spaces are inherently non-injective, as distinct parameter configurations can realize identical functions through functional equivalence. While this symmetry is well understood in classical fully connected and convolutional models, it becomes substantially more intricate in modern attention-based architectures. Existing analyses of multihead attention have largely focused on the vanilla formulation, overlooking positional encodings that fundamentally reshape architectural symmetries. In this work, we provide a formal study of functional equivalence in Transformers with positional encodings. Focusing on the two most widely used variants--sinusoidal and rotary positional encodings (RoPE)--we show that sinusoidal encodings preserve the equivalence structure of vanilla attention, whereas rotary encodings significantly reduce the symmetry group, thereby enhancing expressivity. This offers a principled explanation for the growing prominence of RoPE in practice. We further examine how positional encodings affect linear mode connectivity, and through an alignment algorithm, empirically demonstrate that the presence and variability of connectivity across Transformer settings crucially depend on the positional encoding.

Transformer Grammars (TGs) enhance language modeling by incorporating syntactic tree structures. Despite the potentially significant impact on model performance of how syntactic trees are linearized in TGs, existing studies rely solely on Depth-First Traversal (DFT) for linearization. In this paper, we expand the traversal design space by exploring Breadth-First Traversal (BFT) and a novel hybrid traversal strategy, Production-Rule Traversal (PRT), which combines the structural lookahead of BFT with the early lexical generation of DFT. We integrate these traversal methods with varying tree configurations and masking strategies, and empirically evaluate their performance on language modeling, syntactic generalization and summarization. We reveal the inherent trade-offs between nested composition and global lookahead, providing actionable recommendations for designing task-aware Transformer Grammars.

Large Language Models (LLMs) are increasingly used to guide research methodology, yet their default methodological tendencies under minimal prompting remain unclear. Here, we prompt GPT-5.1, Gemini 3 Pro, and DeepSeek-V3.2 with an LLM-extracted research question from each of 1,000 recent arXiv computer-science papers and compare the resulting methodology suggestions against a paper-derived experimental inventory. Since we provide only the research question, the differences we measure reflect initial suggestions and not how optimal those suggestions are. We extract structured method features from both sources, map them into a shared taxonomy, and quantify divergence across multiple taxonomy dimensions including model provider, dataset task type, and evaluation metric type. The strongest imbalance appears in provider choice, with Jensen-Shannon divergence about 3-5x larger than any other taxonomy dimension. Other/Academic single-occurrence models are underrepresented by 23-24 percentage points, while reused academic/community models are slightly overrepresented (4-6pp). LLMs also suggest a much narrower range of methods overall: the effective number of model entities contracts from 1,232 to 59-96, and inter-LLM rank correlations (0.55-0.68) generally exceed LLM-to-paper correlations (0.33-0.56), so the distortions are largely shared across models. Popularity baselines, BM25 retrieval calibration, and paper-level similarity tests confirm that the outputs are query-specific responses, but filtered through a narrower set of options. Researchers who rely on LLM suggestions without cross-checking therefore risk narrowing their methodological search space toward a more concentrated default.

Machine unlearning has been extensively studied in response to growing privacy concerns and regulatory requirements. However, auditing whether unlearning algorithms have truly erased the influence of specific data remains an open challenge. The lack of reliable and practical auditing mechanisms can lead to critical privacy risks, such as residual information leakage. This paper initiates a systematic investigation into whether existing unlearning algorithms can truly forget the designated data. We propose the first practical and general-purpose auditing framework for machine unlearning, inspired by the concept of proof of ignorance. Our framework addresses the key practicality limitations of existing methods by eliminating the need for retraining-from-scratch baselines, avoiding the training of large numbers of shadow models, and requiring no intrusive intervention in the original training process. To evaluate the effectiveness of our framework, we first conduct validation experiments to verify its soundness and completeness. We then perform comprehensive experiments across six datasets and ten representative unlearning methods. The results demonstrate that our framework reliably distinguishes between successful and failed unlearning. In particular, we observe that retraining-based and fine-tuning-based methods can achieve effective unlearning, even when the target data remain in the original dataset. In contrast, de-optimization-based methods fail to achieve true unlearning and instead degrade the model's performance. Fisher/Hessian-based methods also fail to unlearn requested data, even formal certification is provided. Moreover, we show that our framework is robust against fake unlearning attempts and generalizes well to large language models.

Large language models (LLMs) have shown promise in automating scientific peer review. However, existing approaches often struggle to generate in-depth reviews supported by concrete evidence. We argue that a key limitation is the lack of flexibility to proactively investigate suspicious parts of a paper based on accumulated evidence, as human reviewers do. In this paper, we explore how to enable an LLM-based review agent to perform such proactive investigation. We find that this can be naturally formulated as a Markov Decision Process (MDP), and propose ProReviewer, a scientific peer review agent that proactively reviews a paper guided by a maintained, structured review log. The structured review log serves as a workspace for the agent to track evidence and intermediate findings collected during review. Experiments show that ProReviewer with an 8B backbone, trained by supervised fine-tuning and optimized by reinforcement learning, achieves the highest average score across five quality dimensions, outperforming prompt-based methods with much larger frontier LLMs by up to 39% and the strongest fine-tuned baseline by 16% relatively. It also attains the highest win rates against baselines in human evaluation.

Hierarchical vision-language-action (Hi-VLA) systems have emerged as a promising paradigm for complex robot manipulation, by using high-level VLM planners to decompose tasks into language subgoals executed by low-level VLA controllers. Despite recent empirical progress, there is a lack of unified design principles for these systems: existing Hi-VLA systems differ in how they choose and connect planners, controllers, mechanisms to switch between the two, and how observations and memory are represented in the planner. In this paper, we present a systematic study of Hi-VLA design for robot manipulation. We unify representative Hi-VLA agents under an options-style control framework and benchmark core design choices across short-horizon, long-horizon, and reasoning-intensive tasks. Our analysis distills practical principles for building Hi-VLA systems, showing how model choices and interface mechanisms jointly shape performance. Applying these principles yields a substantially stronger system than either flat VLA control or a naively designed hierarchy, across experiments both in simulation and on a real ALOHA robot. Overall, our results provide a foundation for building more capable, robust, and principled hierarchical VLA agents. More information and video at jiahenghu.github.io/hi-vla.

Spatio-temporal graph neural networks (STGNNs) have become the dominant approach for traffic prediction, yet their computational requirements pose challenges for practical deployment in intelligent transportation systems (ITS). While recent work has proposed efficient alternatives to STGNNs, a fundamental question remains unexplored: are these architectures themselves over-parameterised? We examine this question using the Spatio-Temporal Graph Convolutional Network (STGCN), one of the most widely adopted models in this domain. Through systematic experiments across four diverse traffic datasets, we compare 1-block, 2-block (standard), and 3-block STGCN variants. Our findings reveal that the single-block architecture achieves optimal performance for short-term prediction (10 mins) on three of four datasets, while incurring only marginal degradation ($\leq$1.8% relative error) at longer horizons. Crucially, the 2-block variant incurs 61% higher CPU inference latency and 37% lower throughput relative to 1-block -- substantial overhead for resource-constrained ITS deployment. The 3-block architecture offers no favourable tradeoff, more than doubling computational cost for $<$0.5% relative improvement. These results suggest that the default 2-block STGCN may be over-parameterised for many applications, with implications for both practitioners deploying traffic prediction systems and researchers benchmarking efficiency-focused methods.

LiDAR-based 3D Multi-Object Tracking (MOT) typically relies solely on geometric information, which is often insufficient to distinguish between targets during prolonged occlusions or in crowded human-populated environments. While integrating RGB-based Re-Identification (ReID) offers a theoretical solution for preserving identity context, existing approaches often rely on computationally expensive parallel detectors that hinder real-time robot responsiveness. This work presents a systematic study of image-based ReID in online 3D MOT, utilizing a lightweight projection-based framework to decouple geometric and appearance modeling for mobile robots. A comprehensive analysis of feature extraction architectures is conducted, employing lightweight CNNs and Vision Transformers, and evaluating various multi-modal data association strategies to balance computational latency with robust tracking. Experiments on the Pedestrian class of the KITTI dataset reveal that naive linear fusion, of appearance and motion costs, degrades performance due to visual noise. Conversely, a cascaded matching strategy successfully recovers occluded tracks without compromising overall precision, effectively preventing identity switches to maintain human-robot interaction continuity. We show that lightweight architectures can offer an optimal trade-off between the low latency required for safe navigation and the discriminative power needed for social awareness.

Real-time autonomous driving commonly relies on sampling-based trajectory planners that link candidate trajectories to target waypoints along the road centerline. The placement of these waypoints directly impacts both the existence and quality of feasible trajectories. Yet, its effect on planner performance remains largely unexplored. In this paper, we treat waypoint placement as a first-class design variable. We hold the trajectory primitive and candidate budget fixed, and systematically sweep three placement strategies (uniform spacing, an augmented Ramer-Douglas-Peucker variant (RDP*), and a novel curvature-conditioned allocation) across 449 configurations and five CommonRoad maps of increasing geometric complexity. Our results show that the nominal inter-waypoint spacing $d_s$ is the primary performance driver, with large differences in planner reliability attributed to placement alone. Uniform sampling at a well-tuned spacing matches or surpasses both RDP* and the centered curvature variant. The curvature variant offers a small but consistent advantage on geometrically complex roads under reliability-first and balanced weightings, while RDP* never outperforms uniform sampling. These findings suggest that $d_s$ should be treated as the dominant tuning parameter, with geometry-aware strategies reserved for curvature-rich corridors where feasibility is the limiting factor.

Interpretable linguistic features offer a promising approach for explaining why a given text appears machine-generated, particularly for non-expert users. However, existing findings on which features reliably indicate LLM-generated text remain fragmented across feature sets, models, and text domains. To address this gap, we conduct a large-scale empirical study assessing the robustness of linguistic signals for characterizing AI-generated text. Our analysis covers 284 interpretable linguistic features across outputs from 27 LLMs and ten text domains under cross-model and cross-domain generalization settings. We show that classifiers based solely on linguistic features can reliably distinguish AI-generated from human-written text. However, many previously proposed indicators prove strongly context-dependent, with the exception of measures of lexical richness, which remain robust signals across model families and text domains. These results demonstrate which linguistic signals generalize across contexts and provide a foundation for more reliable, interpretable analyses of AI-generated language.

Latent diffusion models leverage visual tokenizers to compress images into latent spaces for efficient generative modeling. However, better reconstruction quality of a tokenizer does not necessarily translate into better generation quality, suggesting that latent representations should be evaluated not only by fidelity but also by their diffusability. Recent studies have proposed diverse explanations for diffusion-friendly latent spaces, including semantic separability, affine equivariance, distribution uniformity, spatial structure, spectral smoothness, and manifold continuity. Yet these properties are often validated on a limited set of tokenizers, leaving it unclear which factors are most predictive of downstream generation quality and whether such conclusions hold beyond the specific settings in which they are introduced. In this work, we conduct a systematic study of latent diffusability by training a large collection of tokenizers with diverse regularization strategies, architectures, and latent configurations, and evaluating them with multiple downstream diffusion backbones. Our analysis identifies several latent properties that consistently correlate with generation quality and exhibit strong generalization across experimental settings. Beyond existing metrics, we introduce Velocity Irreducible Variance (VIV), a measure of velocity ambiguity induced by trajectory crossings. Extensive experiments show that VIV is one of the most stable predictors of generation quality.

Transformers have become the standard solution for various AI tasks, with the query, key, and value (QKV) attention formulation playing a central role. However, the individual contribution of these three projections and the impact of omitting some remain poorly understood. We systematically evaluate three projection sharing constraints: a) Q-K=V (shared key-value), b) Q=K-V (shared query-key), and c) Q=K=V (single projection). The last two variants produce symmetric attention maps; to address this, we also explore asymmetric attention via 2D positional encodings. Through experiments spanning synthetic tasks, vision (MNIST, CIFAR, TinyImageNet, anomaly), and language modeling (300M and 1.2B parameter models on 10B tokens), we discovered that our transformers perform on par or occasionally better than the QKV transformer. In language modeling, Q-K=V projection sharing achieves 50% KV cache reduction with only 3.1% perplexity degradation. Crucially, projection sharing is complementary to head sharing (GQA/MQA): combining Q-K=V with GQA-4 yields 87.5% cache reduction, while Q-K=V + MQA achieves 96.9%, enabling practical on-device inference. We show that Q-K=V preserves quality because keys and values can occupy similar representational spaces and attention operates in a low-rank regime, whereas Q=K-V breaks attention directionality. Our results systematically characterize projection sharing as an underexplored instance of weight tying in attention, with direct, quantifiable inference memory benefits, particularly valuable for edge deployment. The code is publicly available at https://github.com/Brainchip-Inc/Do-Transformers-Need-3-Projections

Tool-augmented multimodal agents show strong benchmark gains, often taken as evidence that agents have learned to use tools. We argue that this interpretation can be premature: a tool-call trace alone does not show whether the tool supplied answer-critical information. We study two representative ``thinking with images'' agents, Thyme and DeepEyesV2, across real-world understanding, OCR, chart understanding, and mathematical reasoning. Each agent is compared with its Tool-Free counterpart and with a Pure-Text Reasoner trained from the same source pool without tool-calling trajectories. Tool access yields little consistent aggregate improvement, does not reliably reduce generated-token cost, and leaves only a small tool-only solved set: 93% of DeepEyesV2's tool-solved problems and 96% of Thyme's are also solved by at least one non-tool setting. Mechanism ablations further show that the full tool-use loop does not consistently outperform either the tool-call format or the returned execution result alone. In the settings we study, the analyzed agents appear to learn tool-calling patterns more reliably than tool-contributed capabilities, suggesting that evaluation should distinguish tool availability from whether tools actually expand what agents can solve.

We investigate how teacher-student capacity relationships modulate knowledge distillation (KD) effectiveness in ResNet-based image classification on CIFAR-10. Across four teacher-student pairs (R50->R18, R34->R18, R50->R34, and R101->R34) we compare Logit-KD and Feature-KD under a strict evaluation protocol: hyperparameters and checkpoints are selected on a held-out validation split, selected configurations are re-run with five seeds, and the test set is used exclusively for final reporting. Beyond accuracy, we measure distillation fidelity directly via teacher-student agreement and KL divergence. We report four findings. First, the student-capacity pattern survives the corrected protocol at reduced magnitude: the only statistically significant gains occur for R34 students under Feature-KD (+0.19 and +0.21 pp, p<0.05), in two pairs whose teachers differ two-fold in parameters but not in accuracy, localizing the moderating variable on the student side, while no KD gain for R18 students is distinguishable from zero. Second, Feature-KD matches or outperforms Logit-KD in all four pairs, and its students land closer to the teacher's output distribution (KL at T=1) than Logit-KD students despite never observing teacher logits. Third, top-1 teacher-student agreement is flat across all pairs, decoupling fidelity from accuracy gains. Fourth, architecture dominates KD: correcting the ResNet stem for 32x32 inputs is worth +5.5 to +7.2 pp, more than 25x the largest KD gain. We also retract an attribution made in v1: a controlled re-run shows the reported gradient-clipping bug had no measurable effect, and v1's larger gains are explained by test-set selection. Code and results: github.com/umutonuryasar/kd-capacity-gap (tag v2.0).

Scientific data annotation, such as tracking animals in video or proofreading neural reconstructions, remains bottlenecked by the "last mile" problem: even with strong automation, verification and correction consume substantial human effort. Standard approaches train models to directly predict annotations, discarding the rich supervision in how experts navigate, click, verify, and correct. We introduce a framework for studying behavioral cloning on scientific annotation: 9 synthetic tasks paired with synthetic annotations that simulate realistic human strategies including exploration, mistake correction, and strategic decision-making. Our experiments reveal several findings. First, skills emerge hierarchically: models learn GUI mechanics before task-critical decisions, and commit fewer mistakes than the training data while retaining the ability to correct errors when they occur. Second, scaling models on multi-task behavioral cloning shows that larger models are more data efficient within our scale range. Third, multi-task pretraining enables efficient fine-tuning to new tasks, while training from scratch fails entirely. Fourth, linear probes reveal that models internally represent latent variables of the annotation process such as task phase and data position; interestingly, we find a shared mistake representation that generalizes across different annotation tasks. Overall, our framework establishes systematic benchmarks and identifies key bottlenecks, providing a foundation for scaling behavioral cloning to real-world scientific data annotation.

Large Vision-Language Models (LVLMs) extend large language models with visual understanding, but remain vulnerable to hallucination, where outputs are fluent yet inconsistent with images. Recent studies link this issue to language bias-the tendency of LVLMs to over-rely on text while neglecting visual inputs. Yet most analyses remain empirical without uncovering its underlying cause. In this paper, we provide a systematic study of language bias and identify its root in modality misalignment during training. Our analysis shows that both Visual Instruction Tuning (VIT) and Direct Preference Optimization (DPO) often prioritize textual improvements, which may cause LVLMs to overly lean toward language modeling rather than balanced multimodal understanding. To address this, we propose two simple yet effective methods: Language Bias Regularization (LBR) which mitigates language bias through regularization during instruction tuning, and Language Bias Penalty (LBP), which penalizes language bias in the DPO training process. Extensive experiments across diverse models and benchmarks demonstrate the effectiveness of our approach. LBR consistently improves performance on over ten general benchmarks, while LBP significantly reduces hallucination and improves trustworthiness. Together, these methods not only mitigate language bias but also advance the overall alignment of LVLMs, all without introducing any additional data or auxiliary models. Our code is publicly available at https://github.com/lab-klc/LVLM-Language-Bias.

Language agents increasingly improve by reusing \emph{skills} -- structured procedural artifacts distilled from past experience. In particular, \emph{domain-level} and \emph{model-generated} skills are especially promising. They offer fast adaptation within a domain by encoding domain-specific recurring procedures, and they scale beyond labor-intensive hand-crafting. However, while extraction methods continue to proliferate, understanding remains limited, with no comprehensive study spanning the full skill lifecycle -- \textbf{experience generation}, \textbf{skill extraction}, and \textbf{skill consumption} -- to ask whether such skills actually work, when they work, and what makes them succeed or fail. To close this gap, we build a utility-grounded evaluation framework that provides systematic experimental results across extractors and target agents, covering five diverse agentic task domains. We find that model-generated skills are beneficial on average but exhibit non-trivial negative transfer, and that neither extractors nor targets behave uniformly. A model can be a strong extractor yet a weak consumer, or vice versa, with skill utility independent of model scale or baseline task strength. To explain these patterns, we then dissect each lifecycle stage in depth, analyzing how experience composition shapes skill quality, what properties characterize useful skills, and how the same skill transfers across different consumers. Finally, we translate these findings into a concrete \emph{meta-skill} that guides skill extraction toward the features tied to actual utility, which consistently improves skill quality across domains and substantially reduces negative transfer.

Detecting Schwartz values in political texts is hard: cues are often implicit, and neighboring values differ by fine distinctions. Two remedies are widely assumed to help: more surrounding document text, and explicit moral knowledge. Knowledge-based retrieval has improved benchmarks elsewhere, but whether either transfers here is untested, because published systems vary context, knowledge, and model family at once. We separate these factors under matched conditions on the ValuesML/Touché ValueEval format. The input ranges from the target sentence to a local window to the full document. Retrieval is either absent or drawn from a curated moral knowledge base, injected by early, late, or cross-attention fusion. Supervised DeBERTa-v3 encoders are compared against zero-shot LLMs from 12B to 123B. More context is not uniformly better: full-document input improves the encoders by 2.5-3.8 macro-F1 points but does not consistently help the LLMs. Retrieved knowledge helps more reliably, improving every model family and context under early fusion. A control substituting random knowledge-base entries shows the families gain differently: LLMs from relevance, encoders from exposure to the value ontology. Neither larger encoders nor larger LLMs guarantee gains, and early fusion outperforms both trainable variants. Value-sensitive NLP should evaluate context, knowledge, and model family jointly.

Kolmogorov-Arnold Networks (KANs) have demonstrated an exceptional ability to learn complex functions on clean, low-dimensional data but struggle to maintain performance on noisy and imperfect real-world datasets. In contrast, conventional multi-layer perceptrons (MLPs) are far more tolerant to noise and computationally efficient. Replacing all MLP components with KANs in HAR models often degrades accuracy and computation efficiency, highlighting an open challenge: how to combine KANs' precision with MLPs' noise robustness and efficiency. To address this, we systematically explore various placements of KAN modules within deep HAR networks and propose a hybrid architecture that strategically synergizes the strengths of both paradigms, which uses a KAN-based input embedding layer, retains MLP layers for intermediate feature mixing, and introduces a specialized LarctanKAN module for final activity classification. Across eight public HAR datasets, the hybrid KAN-MLP model achieves an average macro F1 score relative improvement of 5.33% compared pure-MLP model, significantly outperforming standalone KAN and MLP baselines. Furthermore, integrating this hybrid strategy into other state-of-the-art HAR architectures consistently boosts their performance. Our findings demonstrate that a carefully orchestrated combination of KAN, MLP, or other conventional neural components yields more robust and accurate HAR models for real-world wearable sensing environments.

The rapid evolution of Large Language Model (LLM) agents has produced diverse interaction paradigms, yet few production systems integrate multiple paradigms within a unified architecture. This paper presents a systematic analysis of three principal agent interaction paradigms, including Multi-Agent Orchestration (Generator-Evaluator), ReAct Tool-Use Loops, and Memory-Augmented Interaction, as implemented in buddyMe, an open-source multi-model agent programming framework. We formalize a five-stage processing pipeline: Requirement Pre-Review -> Task Decomposition -> ReAct Execution -> Real-Execution Verification -> Adversarial Evaluation Discussion, and establish a six-dimensional evaluation schema with weighted scoring. Through four empirical case studies drawn from real-world deployment logs covering museum guide generation, scheduled weather tasks, and comprehensive tour planning, we draw three key conclusions. First, Generator-Evaluator pre-review detects requirement omissions in 20 percent of complex tasks, with 80 percent tasks passing initial inspection. Second, the ReAct loop ensures stable subtask execution but leads to around 30 percent redundant tool invocations. Third, adversarial Evaluator-Defender discussions reach consensus within 2-3 rounds for nearly 70 percent of scenarios, functioning mainly for content refinement rather than logical reversal. We additionally provide three Mermaid-based architectural diagrams and conduct cross-paradigm comparisons with CrewAI, AutoGen, LangGraph, MemGPT and A-Mem across six system dimensions. The research outcomes offer practical design guidelines for constructing stable and reliable multi-paradigm agent systems.

In recent years, computer vision has witnessed remarkable progress, fueled by the development of innovative architectures such as Convolutional Neural Networks (CNNs), Generative Adversarial Networks (GANs), diffusion-based architectures, Vision Transformers (ViTs), and, more recently, Vision-Language Models (VLMs). This progress has undeniably contributed to creating increasingly realistic and diverse visual content. However, such advancements in image generation also raise concerns about potential misuse in areas such as misinformation, identity theft, and threats to privacy and security. In parallel, Mamba-based architectures have emerged as versatile tools for a range of image analysis tasks, including classification, segmentation, medical imaging, object detection, and image restoration, in this rapidly evolving field. However, their potential for identifying AI-generated images remains relatively unexplored compared to established techniques. This study provides a systematic evaluation and comparative analysis of Vision Mamba models for AI-generated image detection. We benchmark multiple Vision Mamba variants against representative CNNs, ViTs, and VLM-based detectors across diverse datasets and synthetic image sources, focusing on key metrics such as accuracy, efficiency, and generalizability across diverse image types and generative models. Through this comprehensive analysis, we aim to elucidate Vision Mamba's strengths and limitations relative to established methodologies in terms of applicability, accuracy, and efficiency in detecting AI-generated images. Overall, our findings highlight both the promise and current limitations of Vision Mamba as a component in systems designed to distinguish authentic from AI-generated visual content. This research is crucial for enhancing detection in an age where distinguishing between real and AI-generated content is a major challenge.

Iterative self-refinement is a simple inference-time strategy for machine translation: an LLM revises its own translation over multiple inference-time passes. Yet document-scale refinement remains poorly understood: 1) which pipelines work best, 2) what quality dimensions improve, and 3) how refiners behave. In this paper, we present a systematic study of document-level literary translation, covering nine LLMs and seven language pairs. Across nine translation-refinement granularity combinations and five refinement strategies, we find a robust recipe: document-level MT followed by segment-level refinement yields strong and stable improvements. In contrast, document-level refinement often makes fewer edits and leads to smaller or less reliable gains. Beyond granularity, A simple general refinement prompt consistently outperforms error-specific prompting and evaluate-then-refine schemes. Our large-scale human evaluation shows that refinement gains come primarily from fluency, style, and terminology, with limited and less consistent improvements in adequacy. Experiments varying model strength reveal refinement projects outputs toward the refiner's distribution rather than performing targeted error repair. These findings clarify the mechanisms and limitations of current refinement approaches.

Specialized foundation models are beginning to emerge in various medical subdomains, but pretraining methodologies and parametric scaling with the size of the pretraining dataset are rarely assessed systematically and in a like-for-like manner. This work focuses on foundation models for electrocardiography (ECG) data, one of the most widely captured physiological time series world-wide. We present a comprehensive assessment of pretraining methodologies, covering five different contrastive and non-contrastive self-supervised learning objectives for ECG foundation models, and investigate their scaling behavior with pretraining dataset sizes up to 11M input samples, exclusively from publicly available sources. Pretraining strategy has a meaningful and consistent impact on downstream performance, with contrastive predictive coding (slightly ahead of JEPA) yielding the most transferable representations across diverse clinical tasks. Scaling pretraining data continues to yield meaningful improvements up to 11M samples for most objectives. We also compare model architectures across all pretraining methodologies and find evidence for a clear superiority of structured state space models compared to transformers and CNN models. We hypothesize that the strong inductive biases of structured state space models, rather than pretraining scale alone, are the primary driver of effective ECG representation learning, with important implications for future foundation model development in this and potentially other physiological signal domains.

Current Large Multimodal Models (LMMs) struggle with spatial reasoning tasks requiring viewpoint-dependent understanding, largely because they are confined to a single, static observation. We propose Thinking with Novel Views (TwNV), a paradigm that integrates generative novel-view synthesis into the reasoning loop: a Reasoner LMM identifies spatial ambiguity, instructs a Painter to synthesize an alternative viewpoint, and re-examines the scene with the additional evidence. Through systematic experiments we address three research questions. (1) Instruction format: numerical camera-pose specifications yield more reliable view control than free-form language. (2) Generation fidelity: synthesized view quality is tightly coupled with downstream spatial accuracy. (3) Inference-time visual scaling: iterative multi-turn view refinement further improves performance, echoing recent scaling trends in language reasoning. Across four spatial subtask categories and four LMM architectures (both closed- and open-source), TwNV consistently improves accuracy by +1.3 to +3.9 pp, with the largest gains on viewpoint-sensitive subtasks. These results establish novel-view generation as a practical lever for advancing spatial intelligence of LMMs.

The real world unfolds along a single set of physics laws, yet human intelligence demonstrates a remarkable capacity to generalize experiences from this singular physical existence into a multiverse of games, each governed by entirely different rules, aesthetics, physics, and objectives. This omni-reality adaptability is a hallmark of general intelligence. As Artificial Intelligence progresses towards Artificial General Intelligence, the multiverse of games has evolved from mere entertainment into the ultimate ground for training and evaluating AGI. The pursuit of this generality has unfolded across four eras: from environment-specific symbolic and reinforcement learning agents, to current large foundation models acting as generalist players, and toward a future creator stage where agent both creates new game worlds and continually evolves within them. We trace the full lifecycle of a generalist game player along four interdependent pillars: Dataset, Model, Harness, and Benchmark. Every advance across these pillars can be read as an attempt to break one of five fundamental trade-offs that currently bound the whole system. Building on this end-to-end view, we chart a five-level roadmap, progressing from single-game mastery to the ultimate creator stage in which the agent simultaneously creates and evolves within theoretical game multiverse. Taken together, our work offers a unified lens onto a rapidly shifting field,and a principled path toward the omnipotent generalist agent capable of seamlessly mastering any challenge within the multiverse of games, thereby paving the way for AGI.

Tool-enabled AI agents are increasingly deployed in cloud-hosted environments and offered as services, where they perform side-effecting operations through privileged tools within execution environments. While such agents enable powerful automation, the security implications of hosting autonomous agents in privileged execution environments are not yet fully explored. This paper presents a structured analysis of security risks associated with cloud-hosted AI agents. We introduce a taxonomy of risk categories, illustrate these risks through three representative agent scenarios, and discuss mitigation strategies along with their tradeoffs. A small controlled experiment empirically illustrates risk manifestation and the effect of lightweight mitigations in this setup. Our analysis suggests that many risks in autonomous cloud agents arise not from novel vulnerabilities, but from over-privileged tools, capability-intent mismatches, and ambient authority leakage in execution environments. Based on these findings, we derive practical design guidelines for deploying AI agents in the cloud more securely.

The evolution of generative models from next-token predictors to autonomous engines of complex systems necessitates rigorous safety hardening. Adversarial jailbreaking, the strategic manipulation of models to elicit harmful output, remains a primary threat to safe deployment. While Reinforcement Learning (RL) frames jailbreaking as a multi-step attack through sequential optimization, a mechanistic understanding of why the framework succeeds remains incomplete. To fill this gap, we present the first systematic decomposition of RL jailbreaking. We deconstruct the framework into problem formalization (reward function, action space, episode length), and algorithmic measures (RL algorithm, training data, reward-shaping) to identify the structural determinants of adversarial success. Our results reveal that the RL-jailbreaker successfully compromised all targeted models and safeguards. Through this first-of-its-kind analysis, we demonstrate that environment formalization, specifically dense rewards and extended episode lengths, is the primary driver of jailbreaking success. This work provides a tool for improving RL-jailbreaker efficiency and, ultimately, harden generative models resistant to RL-based attacks.

Large language models (LLMs) employ safety mechanisms to prevent harmful outputs, yet these defenses primarily rely on semantic pattern matching. We show that encoding harmful prompts as coherent mathematical problems -- using formalisms such as set theory, formal logic, and quantum mechanics -- bypasses these filters at high rates, achieving 46%--56% average attack success across eight target models and two established benchmarks. Crucially, the effectiveness depends not on mathematical notation itself, but on whether a helper LLM deeply reformulates the harmful content into a genuine mathematical problem: rule-based encodings that apply mathematical formatting without such reformulation perform no better than unencoded baselines. We introduce a novel Formal Logic encoding that achieves attack success comparable to Set Theory, demonstrating that this vulnerability generalizes across mathematical formalisms. Additional experiments with repeat post-processing confirm that these attacks are robust to simple prompt augmentation. Notably, newer models (GPT-5, GPT-5-Mini) show substantially greater robustness than older models, though they remain vulnerable. Our findings highlight fundamental gaps in current safety frameworks and motivate defenses that reason about mathematical structure rather than surface-level semantics.

Machine unlearning in Vision-Language Models (VLMs) is required for compliance with the General Data Protection Regulation (GDPR), yet current evaluation practices are inconsistent. We present the first systematic study of metric reliability in multimodal unlearning. Five standard metrics, Forget Accuracy (FA), Retain Accuracy (RA), Membership Inference Attack (MIA), Activation Distance (AD), and JS divergence (JS), yield conflicting method rankings across three VQA benchmarks (MLLMU-Bench, UnLOK-VQA, MMUBench). Kendall tau analysis over 36 unlearned LLaVA-1.5-7B models reveals two opposing clusters, {FA, RA, MIA} and {AD, JS}, with tau_FA_AD = -0.26, reproduced on BLIP-2 OPT-2.7B. Agreement is lower in multimodal VQA (average tau = 0.086) than in unimodal classification (average tau = 0.158; difference = 0.072), indicating that dual image-and-text pathways amplify inconsistency. We introduce the Unified Quality Score (UQS), a composite metric with weights derived from each metric's Spearman correlation with the oracle distance d(M_hat, M_star), where M_star is the oracle model retrained only on the retain set. RA shows the strongest reliability (rho = 0.484, p = 0.003), while FA is negatively correlated (rho = -0.418, p = 0.011). UQS yields stable rankings under 100 random weight perturbations (tau = 0.647 +- 0.262). We release the benchmark, 36 checkpoints, and an interactive leaderboard. Code and pre-computed results are available at https://github.com/neurips26/UnifiedUnl.

Security analysts are overwhelmed by the volume of alerts and the low context provided by many detection systems. Early-stage investigations typically require manual correlation across multiple log sources, a task that is usually time-consuming. In this paper, we present an experimental, agentic workflow that leverages large language models (LLMs) augmented with predefined queries and constrained tool access (structured SQL over Suricata logs and grep-based text search) to automate the first stages of alert investigation. The proposed workflow integrates queries to provide an overview of the available data, and LLM components that selects which queries to use based on the overview results, extracts raw evidence from the query results, and delivers a final verdict of the alert. Our results demonstrate that the LLM-powered workflow can investigate log sources, plan an investigation, and produce a final verdict that has a significantly higher accuracy than a verdict produced by the same LLM without the proposed workflow. By recognizing the inherent limitations of directly applying LLMs to high-volume and unstructured data, we propose combining existing investigation practices of real-world analysts with a structured approach to leverage LLMs as virtual security analysts, thereby assisting and reducing the manual workload.

We investigate linguistic biases in LLM-based restaurant and product recommendations given prompts varying across Southern American English (AE), Indian English (IE), and Code-Switched Hindi-English dialects, using the Yelp Open dataset (Yelp Inc., 2023) and Walmart product reviews dataset (PromptCloud,2020). We add lists of restaurant and product names balanced by cuisine type and product category to the prompts given to the LLM, and we zero-shot prompt the LLMs in a cold-start setting to select the top-20 restaurant and product recommendations from these lists for each of the dialect-varied prompts. We prompt LLMs using different list samples across 20 seeds for better generalization, and aggregate per cuisine-type and per category response counts for each seed, question/prompt, and LLM model. We run mixed-effects regression models for each model family and topic (restaurant/product) with the aggregate response counts as the dependent, and conduct likelihood ratio tests for the fixed effects with post-hoc pairwise testing of estimated marginal means differences, to investigate group-level differences in recommendation counts by model size and dialect type. Results show that dialect plays a role in the type of restaurant selected across the models tested with the mistral-small-3.1 model and both the llama-3.1 family models tested showing more sensitivity to Indian English and Code-Switched prompts. In terms of product recommendations, the llama-3.1-70B-model is particularly sensitive to Code-Switched prompts in four out of seven categories, and more beauty and home category recommendations are seen when using the Indian English and Code-Switched prompts for larger and smaller models, respectively. No broad trends are seen in the model-size based differences, with differing recommendations based on model sizes conditioned by the type of dialect.

Graph-based anti-money laundering (AML) systems on blockchain networks can score suspicious activity at two granularity levels -- transactions or actor addresses -- yet compliance action is conducted per actor. This paper contributes an evaluation methodology for measuring how scoring granularity affects investigation queue composition under fixed review budgets. We formalize the evaluation through a projection framework mapping transaction-level scores to the actor-level action unit via four aggregation operators, and introduce budgeted investigation metrics -- yield@budget, burden decomposition, and case fragmentation. Using the public Elliptic++ Bitcoin dataset (203,769 transactions; 822,942 address occurrences), we train independent random forest classifiers at each level under a causal temporal protocol and compare review queues through Jaccard overlap, burden decomposition, and feature-matching ablations. At one-percent budget, temporal evaluation yields mean Jaccard of 0.374 (SD 0.171); static pooled evaluation yields 0.087 (95% CI [0.079, 0.094]). An enriched address model receiving all 237 features produces even lower overlap (Jaccard=0.051), with 4.3% illicit per 100 reviews versus 30.2% for the transaction-projected queue. Address-level detection value is temporally concentrated: two timesteps exceed 91% illicit per 100 reviews while the static burden is only 3.4%. A fixed hybrid policy underperforms the best single-level queue by 5.05pp (CI [-10.2pp, -0.9pp]). These findings establish that scoring granularity is a consequential design variable for AML investigation systems -- same data, same budget, different queues, different addresses investigated.

Reward hacking in code generation, where models exploit evaluation loopholes to obtain high reward without correctly solving the intended task, poses a critical challenge for Reinforcement Learning (RL) and the deployment of reasoning models. Existing studies often rely on explicitly prompted hacking trajectories, but it remains unclear whether monitors trained on such data can detect reward hacks that arise without direct hacking instructions during RL training. In this work, we introduce Trace-and-Amplify, a framework for scalable curation of reward-hacking trajectories that arise during RL training without explicit hacking instructions. The framework uses unit-test tracers to identify hacking solutions when they occur and retains such trajectories for monitor training and evaluation. Through controlled comparisons between monitors trained on prompt-elicited hacking trajectories and training-time reward-hacking trajectories collected by Trace-and-Amplify, we find that \textbf{(1) prompt-elicited-data-trained monitors often fail to generalize to trajectories curated by our framework}, and \textbf{(2) monitors trained on our Trace-and-Amplify trajectories demonstrate stronger generalizability to unseen hacking types}. Our results indicate that prompted reward hacking data may not fully reflect training-time reward-hacking behaviors, and that relying solely on these data can lead to misleading conclusions. Codebase is available at https://github.com/LichenLillc/CoTMonitoring.git

Dimensionality reduction is a critical preprocessing step for clustering high-dimensional data, yet comprehensive evaluation of its impact across diverse methods and data types remains limited. In this study, we systematically assess the influence of five dimensionality reduction techniques - Principal Component Analysis (PCA), Kernel Principal Component Analysis (Kernel PCA), Variational Autoencoder (VAE), Isometric Mapping (Isomap), and Multidimensional Scaling (MDS) - on the performance of four popular clustering algorithms - k-means, Agglomerative Hierarchical Clustering (AHC), Gaussian Mixture Models (GMM), and Ordering Points to Identify the Clustering Structure (OPTICS). We evaluate clustering quality using the Adjusted Rand Index (ARI), comparing results without and with dimensionality reduction at different reduction levels recommended in the literature (i.e., k-1, where k is the number of clusters, and 25% and 50% of the original number of dimensions). Our findings underscore the importance of a careful selection of the dimensionality reduction technique and the dimensionality reduction level that should be tailored to intrinsic data geometry and clustering algorithms under consideration.

Anti-doping programs rely on biological testing to detect performance-enhancing drugs, but such testing costs over $800 per sample and is limited by short detection windows for many prohibited substances. These constraints leave large portions of athletes without regular testing, motivating complementary screening approaches that analyze routine competition results to identify suspicious performance patterns. We present a system that processes 1.6 million athletics performances from over 19,000 competitions (2010-2025) using eight detection methods ranging from statistical rules to machine learning and trajectory analysis. We validate all methods against publicly confirmed anti-doping violations to measure their effectiveness in identifying sanctioned athletes. Trajectory-based methods, which compare performances to expected career progression, achieve the best balance between detecting violations and limiting false alarms, though all methods face challenges from incomplete data and rare confirmed violations. The system provides an interactive interface for expert-driven investigation, emphasizing transparency and human judgment to support, rather than replace, established anti-doping processes.

Electroencephalography (EEG) foundation models have shown strong potential for learning generalizable representations from large-scale neural data, yet their clinical deployment is hindered by distribution shifts across clinical settings, devices, and populations. Test-time adaptation (TTA) offers a promising solution by enabling models to adapt to unlabeled target data during inference without access to source data, a valuable property in healthcare settings constrained by privacy regulations and limited labeled data. However, its effectiveness for EEG remains largely underexplored. In this work, we introduce NeuroAdapt-Bench, a systematic benchmark for evaluating test-time adaptation methods on EEG foundation models under realistic distribution shifts. We evaluate representative TTA approaches from other domains across multiple pretrained foundation models, diverse downstream tasks, and heterogeneous datasets spanning in-distribution, out-of-distribution, and extreme modality shifts (e.g., Ear-EEG). Our results show that standard TTA methods yield inconsistent gains and often degrade performance, with gradient-based approaches particularly prone to heavy degradation. In contrast, optimization-free methods demonstrate greater stability and more reliable improvements. These findings highlight the limitations of existing TTA techniques in EEG, provide guidance for future development, and underscore the need for domain-specific adaptation strategies.

Decoder-only large language models (LLMs) are increasingly replacing BERT-style architectures as the backbone for dense retrieval, achieving substantial performance gains and broad adoption. However, the robustness of these LLM-based retrievers remains underexplored. In this paper, we present the first systematic study of the robustness of state-of-the-art open-source LLM-based dense retrievers from two complementary perspectives: generalizability and stability. For generalizability, we evaluate retrieval effectiveness across four benchmarks spanning 30 datasets, using linear mixed-effects models to estimate marginal mean performance and disentangle intrinsic model capability from dataset heterogeneity. Our analysis reveals that while instruction-tuned models generally excel, those optimized for complex reasoning often suffer a ``specialization tax,'' exhibiting limited generalizability in broader contexts. For stability, we assess model resilience against both unintentional query variations~(e.g., paraphrasing, typos) and malicious adversarial attacks~(e.g., corpus poisoning). We find that LLM-based retrievers show improved robustness against typos and corpus poisoning compared to encoder-only baselines, yet remain vulnerable to semantic perturbations like synonymizing. Further analysis shows that embedding geometry (e.g., angular uniformity) provides predictive signals for lexical stability and suggests that scaling model size generally improves robustness. These findings inform future robustness-aware retriever design and principled benchmarking. Our code is publicly available at https://github.com/liyongkang123/Robust_LLM_Retriever_Eval.