Search research

Sequential editing of structured knowledge in large language models allows targeted factual updates without retraining, yet existing methods often rely on complex regularization or constraint mechanisms whose necessity remains unclear. In this work, we systematically investigate the mechanisms underlying effective and stable sequential editing. Specifically, we first analyze the empirical success of AlphaEdit and establish, via a rigorous optimization analysis, the formal equivalence between one-time and sequential editing. Building on this insight, we generalize the equivalence to a broader class of editing objectives, demonstrating that stability emerges naturally from properly accounting for accumulated editing constraints, rather than from specialized regularization or null-space operations. We empirically confirm that many commonly used regularization strategies are unnecessary for reliable sequential updates. Furthermore, we extend our framework to handle conflicting edits, ensuring robust and consistent behavior under contradictory updates. Ultimately, our work provides Ariadne's thread through the labyrinth of sequential editing, charting a path toward simpler, more interpretable, and dependable knowledge updates. Our code is available at https://github.com/Wangzzzzzzzz/OTE-SE-Alignment.

To improve residents' well-being in Australia's urban areas, governments have introduced policy reforms such as SEPP65, BADS, and SPP7.3 to enhance apartment design quality. These regulations require precise geometric and spatial analysis to evaluate health-related features, including daylight access, natural ventilation, privacy, and space efficiency. However, compliance checking remains challenging due to its manual, time-intensive nature. Additionally, evolving policies limit scalability for large-scale assessments across thousands of apartments. Existing automated floor plan analysis methods are fragmented and typically focus on single apartments, lacking a unified framework for multi-unit compliance checking. This article explores current advancements in automated floor plan analysis, particularly AI-driven approaches, and highlights key challenges in their practical adoption. To address these gaps, a conceptual framework is proposed for automated compliance checking in multi-apartment buildings. A Large Language Model (LLM) is used within a Rule Engine to convert textual building codes into executable, explainable rules. A Data Extraction Engine segments floor plan images into elements such as walls, rooms, fixtures, text, and symbols, and transforms them into a structured building graph with topological relationships. This structured representation is then evaluated by a Compliance Check Engine, which leverages LLM-generated rules for assessment. The proposed framework offers a scalable, consistent, and transparent approach to automated compliance checking across jurisdictions, supporting efficient enforcement of apartment design standards and promoting healthier, higher-density urban development.

Large Language Model (LLM)-based search agents trained with reinforcement learning (RL) have significantly improved the performance of knowledge-intensive tasks. However, existing methods encounter critical challenges in long-horizon credit assignment: (i) Reward Sparsity, where models receive only outcome feedback without step-level guidance to differentiate action quality; (ii) Isolated Credit, where credit is assigned to steps independently, failing to capture sequential dependencies; and (iii) Distributional Shift, where rewards are estimated on templates that deviate from the model's natural generative distribution. To address these issues, we propose Pivot-Based Credit Assignment (PiCA), a novel step reward mechanism that reformulates the search trajectory as a sequential process of cumulative search progress. Unlike prior isolated step rewards, PiCA defines process rewards as success probabilities dependent on the historical context based on Potential-Based Reward Shaping (PBRS). This approach identifies pivot steps, which comprise target golden sub-queries and sub-answers derived from historical trajectories, as information peaks that significantly boost the likelihood of a correct final answer. By anchoring these step rewards to the final task objective, PiCA provides dense, pivot-aware and trajectory-dependent guidance while maintaining distributional consistency. Extensive experiments show that PiCA outperforms existing strong baselines across seven knowledge-intensive QA benchmarks, achieving 15.2% and 2.2% improvements for 3B and 7B models. The consistent performance gains across various models show PiCA's robust generalization. The code is available at https://github.com/novdream/PiCA.

While Multimodal Large Language Models (MLLMs) excel at single-image understanding, they exhibit significantly degraded performance in multi-image reasoning scenarios. Multi-image reasoning presents fundamental challenges including complex inter-relationships between images and scattered critical information across image sets. Inspired by human cognitive processes, we propose a Cognition-Inspired Meta-Action Framework (CINEMA), which decomposes multi-image reasoning into five structured meta-actions: Global, Focus, Hint, Think, and Answer, explicitly modeling the sequential cognitive steps humans naturally employ. For cold-start training, we introduce a Retrieval-Based Tree Sampling strategy that generates high-quality meta-action trajectories to bootstrap the model with reasoning patterns. During reinforcement learning, we adopt a two-stage paradigm: an exploration phase with Diversity-Preserving Strategy to avoid entropy collapse, followed by an annealed exploitation phase with DAPO to gradually strengthen exploitation. To train our model, we construct a dataset of 56k cold-start and 58k reinforcement learning instances spanning multi-image, multi-frame, and single-image tasks. We conduct extensive evaluations on multi-image reasoning benchmarks, video understanding benchmarks, and single-image benchmarks, achieving competitive state-of-the-art performance on several key benchmarks. Our model surpasses GPT-4o on the MUIR and MVMath benchmarks and notably outperforms specialized video reasoning models on video understanding benchmarks, demonstrating the effectiveness and generalizability of our human cognition-inspired reasoning framework.

Music festival lineups emerge from complex relationships among artists, genres, releases, labels, and past performances, making the prediction of future lineups a natural fit for temporal knowledge graph (TKG) forecasting. In this work, we present a TKG covering 380 festivals over 55 years, comprising more than 90K festival performance quadruples along with information on festivals, artist tours, and artist metadata, and release it as a resource for TKG forecasting evaluation. We formalize festival lineup forecasting as temporal link prediction between artists and festivals at future timestamps. We evaluate six TKG forecasting models on this task, analyze their capabilities and limitations, and compare them against Large Language Models applied zero-shot. Our resource complements existing TKG benchmarks by grounding evaluation in a concrete, real-world application domain.

Diffusion language models (dLLMs) can predict many tokens in parallel, but accurate generation still requires many iterative denoising steps. Few-step distillation accelerates decoding by compressing multiple teacher steps into a single student transition. However, existing methods construct supervision on off-policy trajectories. At inference, the student's early parallel commitments alter the context of later predictions, so the states it actually visits drift away from the supervised ones--precisely when step compression is most aggressive. On-policy distillation is a natural remedy for this mismatch, but it leaves open how far each transition should advance: matching only the teacher's next action limits compression, while indiscriminately merging future actions can violate intermediate dependencies. To address this limitation, we propose OPTD, On-Policy Transition Distillation with consistency-guided adaptive compression. It samples partial states from the few-step student's own trajectories, uses a frozen, question-only teacher to identify outcome-aligned future candidates, and orders them by current-state confidence. The method then selects the longest prefix whose joint commitment preserves the teacher's rollout outcome. A set-bottleneck objective promotes every verified future candidate to the decoder's release threshold, while a frozen-teacher KL anchor regularizes all other active positions. Neither target construction nor training uses a gold response. Across four mathematical reasoning and code-generation benchmarks, OPTD consistently improves the quality--efficiency trade-off and attains the strongest overall quality-constrained AUP among the evaluated few-step baselines.

Automated understanding of complex soccer scenarios from video remains a significant challenge for contemporary vision-language models (VLMs), which suffer from shallow cross-modal alignment and exhibit fundamental limitations in multi-step reasoning and coordinated tool integration. We present TreeSoc, a structured reasoning framework that reformulates soccer video question answering as a hierarchical search problem rather than a single-pass prediction. Specifically, TreeSoc employs a dynamic depth-first search (DFS) mechanism that decomposes complex queries into sequentially ordered sub-tasks, enabling iterative reasoning refinement through explicit intermediate states. This tree-structured decomposition naturally supports adaptive tool routing, wherein domain-specific modules are selectively activated and their outputs incorporated at each reasoning node to produce contextually grounded predictions. On SoccerBench, TreeSoc achieves state-of-the-art performance, with accuracies of 85.2%, 87.4%, and 82.2% on TextQA, ImageQA, and VideoQA, respectively. Additionally, TreeSoc further demonstrates strong cross-domain generalization, attaining 74.16% accuracy on NExT-QA. These results establish structured, tool-augmented tree reasoning as an effective paradigm for robust video understanding. Code is available at: https://github.com/thanhnhan29/TreeSoc.

Quasi-bimodal objects, such as text, road signs, and barcodes, play a basic yet vital role in daily visual communication. By boiling these down to clear silhouettes, binarization uses a minimal language to convey essential vision cues for maximum downstream efficiency, especially for tasks that require simple geometric, topological reasoning rather than heavy appearance modeling. The catch is that frame-based imaging often struggles on mobile platforms like drones, self-driving cars, and underwater vehicles, in which rapid motion causes severe motion blur and harsh lighting washes out scene details. To overcome these physical limits, neuromorphic vision via event cameras, featuring microsecond time resolution and high dynamic range, steps in as a natural solution. Building upon this event-driven paradigm, we propose a simple yet effective dual-modal approach that harnesses the synergy between frames and events for training-free, real-time, high-frame-rate binarization on CPU-only devices. Extensive evaluations show that it earns competitive performance against leading techniques in reducing blur artifacts and delivers impressive improvements under challenging illumination at a lower computational cost. Besides, its asynchronous nature bypasses long-standing event-scarcity issues that break traditional time-binning reconstruction at fixed time slots, maintaining clear target shapes even at extreme kilohertz frame rates. Its binary results further serve as reliable representations to facilitate a range of downstream tasks. This work paves the way towards lightweight perception and interaction in embodied intelligence on resource-constrained edge platforms.

Large language model optimization has historically bifurcated into isolated data-centric and model-centric paradigms: the former manipulates involved samples through selection, augmentation, or poisoning, while the latter tunes model weights via masking, quantization, or low-rank adaptation. This paper establishes a unified \emph{data-parameter correspondence} revealing these seemingly disparate operations as dual manifestations of the same geometric structure on the statistical manifold $\mathcal{M}$. Grounded in the Fisher-Rao metric $g_{ij}(θ)$ and Legendre duality between natural ($θ$) and expectation ($η$) parameters, we identify three fundamental correspondences spanning the model lifecycle: 1. Geometric correspondence: data pruning and parameter sparsification equivalently reduce manifold volume via dual coordinate constraints; 2. Low-rank correspondence: in-context learning (ICL) and LoRA adaptation explore identical subspaces on the Grassmannian $\mathcal{G}(r,d)$, with $k$-shot samples geometrically equivalent to rank-$r$ updates; 3. Security-privacy correspondence: adversarial attacks exhibit cooperative amplification between data poisoning and parameter backdoors, whereas protective mechanisms follow cascading attenuation where data compression multiplicatively enhances parameter privacy. Extending from training through post-training compression to inference, this framework provides mathematical formalization for cross-community methodology transfer, demonstrating that cooperative optimization integrating data and parameter modalities may outperform isolated approaches across efficiency, robustness, and privacy dimensions.

LLM watermarks must be detectable without compromising text quality, yet most existing schemes bias the next-token distribution and pay for detection with measurable quality loss. We present SLAM (Structural Linguistic Activation Marking), a novel white-box watermarking scheme that sidesteps this cost by writing the mark into structural geometry rather than token frequencies: sparse autoencoders identify residual-stream directions encoding linguistic structure (e.g., voice, tense, clause order), and we causally steer those directions at generation time, leaving lexical sampling and semantics unconstrained. On Gemma-2 2B and 9B, SLAM achieves 100% detection accuracy with a quality cost of only 1-2 reward points - compared to 7.5-11.5 for KGW, EWD, and Unigram - with naturalness and diversity preserved at near-unwatermarked levels across both models. The trade-off is a complementary robustness profile: SLAM resists word-level edits but is vulnerable to paraphrase that restructures syntax (at a quality cost), the converse of token-distribution methods.

Modern image editors combine vision-language models (VLMs) with diffusion transformer backbones to modify a single reference image according to instructions without fine-tuning. This capability also enables unauthorized manipulation of publicly released images. Existing inference-time defenses either invalidate edits through conspicuous corruption, thereby exposing the protection, or allow them to proceed with identity or reference content drift, thereby failing to prevent the editing behavior itself. We instead target a stealthy and harmless no-op in which the requested edit is suppressed, the output remains natural and source-preserving without conspicuous artifacts or identity replacement, and harmful semantics requested by malicious instructions are absent. We propose NullEdit, which targets the VLM representation jointly formed from the reference image and instruction before it conditions the downstream DiT backbone. Using normal-edit and no-edit anchors, NullEdit redirects this representation, while cross-prompt gradient averaging transfers protection to held out instructions. Across Step1X-Edit and Qwen-Image-Edit on CelebA-HQ and VGGFace2, NullEdit reduces the EditReward IF score by 0.813 on average relative to the SOTA baseline while preserving subject identity and source content.

Building foundation models for medical imaging requires pooling data across institutions, yet privacy regulations prohibit centralized aggregation. Existing Federated Foundation Models either fine-tune natural-image models with poor medical-domain transfer, or train from scratch within a single modality, lacking the flexibility to unify tasks. We identify an under-explored challenge, Imaging Modality Heterogeneity, where clients operate under two structural regimes: Overlapped (shared modalities with heterogeneous label distributions) and Non-overlapped (fully disjoint modalities per client). We propose FM$^2$, a unified framework that trains the core backbone from scratch to preserve medical domain fidelity while optionally incorporating biomedical pretrained encoders for vision-language alignment. FM$^2$ equips each client with dual Mixture-of-Experts modules (a Class-wise MoE for personalized category knowledge and a Domain-wise MoE for shared cross-modality representations), coupled with a Heterogeneous Modality Alignment (HMA) regularizer that explicitly aligns modality-specific expert parameters, admitting provable $O(1/\sqrt{T})$ convergence and generalization guarantees. FM$^2$ further incorporates Caption-Enhanced Learning (CEL), where locally retained GPT-4o-generated captions serve as a textual semantic bridge enabling representation transfer across clients with disjoint modalities, and demonstrates extensibility to Federated Medical VQA. Experiments on our MIMH benchmark (classification and CEL) and real-world medical VQA datasets confirm consistent superiority over state-of-the-art federated baselines and strong out-of-modality generalization across all three tasks.

Large Language Models (LLMs) are increasingly used in healthcare for tasks such as clinical question answering, diagnosis support, and report summarization. Despite their promise, these models remain highly sensitive to subtle prompt perturbations, both lexical and syntactic, posing serious risks in safety-critical clinical applications. In this study, we conduct a systematic sensitivity analysis to evaluate the robustness of both general-purpose (e.g., GPT-3.5, Llama3) and medical-specific LLMs (e.g., ClinicalBERT, BioLlama3, BioBERT) using the MedMCQA benchmark. We categorize perturbations into natural and adversarial types and examine their effect on model consistency, accuracy, and reliability in clinical reasoning tasks. Our findings reveal that medical LLMs are not intrinsically safe. Even minor variations in phrasing can alter clinical advice, and targeted adversarial prompts can provoke harmful outputs. In high-stakes settings like healthcare, such unpredictability is unacceptable-models that change diagnoses due to reworded inputs or hallucinate medications when slightly rephrased cannot be reliably trusted by clinicians. While models tend to show resilience to simple lexical substitutions or paraphrasing, they often break down under syntactic reordering or misleading contextual cues. This fragility is evident across both general-purpose and domain-specific LLMs. Notably, adversarial manipulations can lead to clinically dangerous outputs, such as recommending incorrect dosages or omitting critical findings.

Large language models~(LLMs) have demonstrated remarkable capabilities in code generation, yet their performance remains limited on domain-specific tasks such as Computer-Aided Design~(CAD) code generation, largely due to the scarcity of high-quality training data. In-Context Learning~(ICL) provides a training-free alternative by prompting LLMs with task-specific exemplars, but its effectiveness critically depends on how exemplars are selected. Existing selection strategies mainly rely on similarity or point-wise diversity, often overlooking the compositional nature of CAD design specifications, where a query may involve multiple functional requirements, geometric constraints, and design primitives. As a result, selected exemplars can be individually relevant but collectively redundant, providing insufficient coverage for complex design requirements. In this work, we propose \emph{knowledge sufficiency} as a principled objective for exemplar selection, aiming to select a compact set of exemplars that maximally satisfies the requirements contained in a target design specification. To instantiate this objective, we introduce \emph{Design-Specification Tiling~(DST)}, which estimates knowledge sufficiency through a surrogate tiling ratio by decomposing design specifications into multi-granular components and measuring the proportion of query components covered by selected exemplars. We further show that optimizing this objective can be formulated as a submodular maximization problem, and develop a polynomial-time greedy algorithm tailored to this setting with a $(1-1/e)$-approximation guarantee. Extensive experiments across multiple LLMs demonstrate that DST substantially improves CAD code generation quality and consistently outperforms existing ICL exemplar selection strategies, highlighting the importance of requirement-level knowledge coverage for domain-specific code generation.

Children are naturally energetic, and during their spontaneous activities, they often encounter potentially dangerous situations, especially when lacking parental supervision. Identifying actions that pose risks plays a crucial role in ensuring their safety. This paper build a novel challenging dataset, namely KidRisk, including 2,500 short videos of children's actions and 10,000 images for dangerous action of children. We also introduce a benchmark on our newly constructs dataset and find that traditional deep learning models demonstrated limited effectiveness on these tasks. Therefore, we develop vision-language based baselines with exceptional context understanding of visual information. Our proposed methods achieved an accuracy of 83.53% in classifying children's actions and 96.14% in recognizing children's dangerous actions, significantly outperforming traditional approaches. These results confirm that vision-language models are not only feasible but also highly effective in detecting hazardous actions, contributing positively to safeguarding children's safety.

Multimodal Large Language Models (MLLMs) excel at recognizing individual visual elements and reasoning over simple linear diagrams. However, when faced with complex topological structures involving branching paths, converging flows, and cyclic dependencies, their reasoning capabilities degrade sharply, even on tasks as basic as counting endpoints. Existing benchmarks fail to probe this gap, focusing on semantic comprehension rather than structural reasoning. We introduce ReactBench, a benchmark that reveals fundamental limitations in structural reasoning through chemical reaction diagrams. These real-world scientific diagrams offer an ideal testbed because they naturally span diverse structures from linear chains to cyclic graphs, while requiring both precise local recognition and coherent global reasoning. Our benchmark comprises 1,618 expert-annotated QA pairs across four hierarchical task dimensions. Extensive evaluation across 24 MLLMs reveals a significant performance gap exceeding 30% between anchor-based tasks and holistic structural reasoning tasks. Controlled ablations confirm this bottleneck lies in reasoning, not perception. These findings expose a fundamental deficit in structural understanding and establish directions for advancing visual reasoning.

Recent large language model agents often use external skills as modular procedural units that condition inference and improve complex task solving. Thus, automatically generating high-quality skills from documents or experience has become an important problem. Existing skill generation methods largely rely on heuristics or pipeline-style consolidation, which must be specially designed for different evidence sources. In contrast, learning-based approaches offer a more unified way to model skill generation across heterogeneous sources. However, learning-based skill generation remains challenging because skills lack a natural supervision signal based on relevance or correctness; their value can largely be determined only by whether they improve the behavior of the agent on downstream tasks. To address this challenge, we proposeSkill-$α$, a reinforcement learning method that learns a unified policy for progressive skill generation. Specifically, we construct each skill by repeatedly applying the learned policy to successive source evidence and introduce a novel rollback reward that evaluates each edit by comparing downstream execution under the original and edited skills on an anchored query. Extensive experiments show thatSkill-$α$ generates more effective skills than methods based on heuristics or pipelines in both document-to-skill and experience-to-skill settings. Under the main GPT-4o worker,Skill-$α$ improves average downstream success rates over the strongest skill-generation baseline by 3.1 points on CL-Bench and 6.7 points on tau2-bench. Further ablations and analysis validate the importance of rollback reward and progressive generation.

The pursuit of truth is central to democratic deliberation and governance, yet political discourse reflects varying epistemic orientations, ranging from evidence-based reasoning grounded in verifiable information to intuition-based reasoning rooted in beliefs and subjective interpretation. We introduce a scalable approach to measure epistemic orientation using the Evidence--Minus--Intuition (EMI) score, derived from large language model (LLM) ratings and embedding-based semantic similarity. Applying this approach to 15 million parliamentary speech segments spanning 1946 to 2025 across seven countries, we examine temporal patterns in discourse and its association with deliberative democracy and governance. We find that EMI is positively associated with deliberative democracy within countries over time, with consistent relationships in both contemporaneous and lagged analyses. EMI is also positively associated with the transparency and predictable implementation of laws as a dimension of governance. These findings suggest that the epistemic nature of political discourse is crucial for both the quality of democracy and governance.

Best-of-n sampling improves the accuracy of large language models (LLMs) and large reasoning models (LRMs) by generating multiple candidate solutions and selecting the one with the highest reward. The key challenge for reasoning tasks is designing a scoring function that can identify correct reasoning chains without access to ground-truth answers. We propose Probabilistic Confidence Selection And Ranking (PiCSAR): a simple, training-free method that scores each candidate generation using the joint log-likelihood of the reasoning and final answer. The joint log-likelihood of the reasoning and final answer naturally decomposes into reasoning confidence and answer confidence. PiCSAR achieves substantial gains across diverse benchmarks (+10.18 on MATH500, +9.81 on AIME2025), outperforming baselines with at least 2x fewer samples in 16 out of 20 comparisons. Our analysis reveals that correct reasoning chains exhibit significantly higher reasoning and answer confidence, justifying the effectiveness of PiCSAR.

Reinforcement Learning from Human Feedback (RLHF) relies on reward models to align large language models with human preferences. However, RLHF often suffers from reward hacking, wherein policy learning exploits flaws in the trained reward model to maximize reward scores without genuinely aligning with human preferences. A significant example of such reward hacking is length bias, where reward models usually favor longer responses irrespective of actual response quality. Previous works on tackling length bias have notable limitations, these approaches either mitigate bias without characterizing the bias form, or simply assume a linear length-reward relation. To accurately model the intricate nature of length bias and facilitate more effective bias mitigation, we propose FiMi-RM (Bias Fitting to Mitigate Length Bias of Reward Model), a framework that autonomously learns and corrects underlying bias patterns. Our approach consists of three stages: First, we warm up by training a standard reward model which inherently contains length bias. Next, we deploy a lightweight fitting model to capture the non-linear relation between length and reward. Finally, we incorporate this learned relation into the reward model, effectively decoupling length from reward while preserving preference modeling capabilities. Experimental results demonstrate that FiMi-RM achieves a more balanced length-reward distribution. Furthermore, when applied to alignment algorithms such as Direct Preference Optimization (DPO) and Best-of-N (BoN), our debiased reward model improves length-controlled win rate and reduces verbosity without compromising its performance.

Multimodal large language models (MLLMs) can miss fine details in a full image that they recognize in a closer view. Recovering this evidence requires deciding where to look and how much surrounding context to retain. We present Q-CueGraph, a query-conditioned evidence acquisition method for frozen MLLMs. For text-rich images, it builds a reusable graph of OCR lines and layout relations. Each question activates anchors, expands them into contextual regions, and selects candidates for a single observation window. Query-conditioned object detections support natural-image search through the same region-selection and composition interface. A lightweight candidate scorer further learns which observations support correct answers from frozen-reader feedback and training answers, without evidence-box supervision. Across six benchmarks, we examine the roles of query conditioning, evidence composition, and learned answerability. With Qwen2.5-VL-7B, Q-CueGraph raises V*Bench accuracy from 0.696 to 0.832 using 19.1% of source-image area, and retains 92% of full-image ANLS on InfographicVQA using about half the image area. The analyses show that useful evidence depends on both its relevance to the question and the context available to the reader. Q-CueGraph makes these choices explicit before answer generation.

Effective flood risk management relies on accurate forecasting, yet the "black box" nature of stateof-the-art Deep Learning models creates a barrier to trust and accountability in high-stakes public safety decisions. While existing Explainable AI (XAI) methods offer local attributions, they fail to provide the verifiable, operationally meaningful causal narratives required by disaster response authorities. To address this societal challenge, we propose Context-Aware Concept Distillation (CACD), a framework developed in collaboration with domain experts to distill opaque LSTMs into interpretable, hydrology-aware surrogate models. We introduce an unsupervised pipeline to discover a "Hydrological Language" and a Residual Hypernetwork that dynamically modulates these concepts based on static basin characteristics. Evaluated on 5,203 basins globally, our model achieves high fidelity (Median NSE 0.70), significantly outperforming black-box baselines (e.g., Multi Layer Perceptrons) on unseen future data. By demonstrating that human-interpretable concepts are sufficient to reconstruct flood dynamics, this work balances AI accuracy with the transparency required for responsible environmental decision-making.

Optical Character Recognition (OCR) for Persian remains substantially less mature than for Latin-script languages despite Persian being spoken by more than 110 million people across multiple countries. This gap arises from two fundamental challenges: the intrinsic complexity of the Perso-Arabic writing system and the limited availability of large-scale, high-quality annotated datasets. Persian script exhibits obligatory cursive connectivity, context-dependent glyph shaping, extensive ligatures, diacritic placement, and stylistic variation across writing forms such as Naskh and Nastaliq, all of which significantly complicate text recognition. At the same time, the high cost and labor-intensive nature of manual annotation have created a persistent data bottleneck, limiting the development of robust OCR systems and slowing progress in Persian document digitization.In this paper, we introduce Persian Pixel, a comprehensive synthetic OCR dataset specifically designed to address these challenges. Comprising over 343,000 high-fidelity image text pairs, the dataset spans sentence, paragraph, and full-page document layouts generated from a carefully curated seven-million-word Persian corpus using the SynthOCR-Gen rendering framework. The generation pipeline faithfully models the typographic characteristics of Persian script, including contextual character joining, positional glyph variants, diacritic placement, and multiple representative Persian typefaces. To bridge the synthetic-to-real domain gap, the rendered images are further enriched with more than twenty-five stochastic degradation models that emulate realistic document acquisition artifacts, including ink bleed, paper aging, blur, illumination variation, scanner imperfections, compression artifacts, and multiple noise processes.By overcoming the long-standing scarcity of annotated Persian OCR data, Persian Pixel provides a scalable and openly available resource for training and fine-tuning modern OCR architectures, including transformer-based models such as TrOCR and Donut. The dataset establishes a strong foundation for research in Persian document analysis, historical manuscript digitization, and end-to-end document understanding, while demonstrating that programmatic synthetic data generation offers a practical, cost-effective, and scalable alternative to manual annotation for advancing OCR in low-resource and typographically complex scripts.

Evaluating meeting effectiveness is crucial for improving organizational productivity. Current approaches rely on post-hoc surveys that yield a single coarse-grained score for an entire meeting. The reliance on manual assessment is inherently limited in scalability, cost, and reproducibility. Moreover, a single score fails to capture the dynamic nature of collaborative discussions. We propose a new paradigm for evaluating meeting effectiveness centered on novel criteria and temporal fine-grained approach. We define effectiveness as the rate of objective achievement over time and assess it for individual topical segments within a meeting. To support this task, we introduce the AMI Meeting Effectiveness (AMI-ME) dataset, a new meta-evaluation dataset containing 2,459 human-annotated segments from 130 AMI Corpus meetings. We also develop an automatic effectiveness evaluation framework that uses a Large Language Model (LLM) as a judge to score each segment's effectiveness relative to the overall meeting objectives. Through substantial experiments, we establish a comprehensive benchmark for this new task and evaluate the framework's generalizability across distinct meeting types, ranging from business scenarios to unstructured discussions. Furthermore, we benchmark end-to-end performance starting from raw speech to measure the capabilities of a complete system. Our results validate the framework's effectiveness and provide strong baselines to facilitate future research in meeting analysis and multi-party dialogue. Our dataset and code will be publicly available. The AMI-ME dataset and the Automatic Evaluation Framework are available at: this URL.

Unified vision-language models (VLMs) that tokenize images through a vector-quantized (VQ) codebook routinely hallucinate objects on grounded yes/no benchmarks, yet existing decoding-time fixes treat this as generic miscalibration without an architectural account. Using activation patching across twenty-five models spanning eight LLM families, we identify an early-layer ($L_0$) attention routing circuit shared across VQ-tokenized VLMs and propose a three-gate diagnostic that distinguishes the models carrying it from those that do not. The diagnostic isolates ten positive models (five natural unified-VQ VLMs across three LLM families and five induced variants) and rejects the remaining fifteen. A single-variable architectural swap (LLaVA-1.6 CLIP+MLP $\rightarrow$ VQ+Linear) installs the circuit, while a matched-compute MLP control on identical data does not, isolating vector quantization as the source of the pathological signal; the routing pathway that carries it is one that the backbone already provides. Against tuned VCD and DoLA baselines, tuned DoLA wins on binary calibration, but \textbf{only $L_0$ ablation reduces object hallucination in open-ended generation} (CHAIR$_i$ reduces by $31\,\%$ relatively, whereas tuned DoLA and VCD leave it unchanged or worsen it). These results recast object hallucination in unified VQ VLMs as a property of architecture and pretraining, and yield a targeted intervention that mechanism-agnostic decoding cannot replicate.

Large language models (LLMs) often encounter conflicting prompts, although current instruction following benchmarks assess those meta-instructions in isolation, limiting the insights about how models process conflicting instructions. We introduce a framework \textit{PRIME}(\textit{Prompt Resolution under Incompatible Meta-Instructions Evaluation}) to analyze behavior of LLMs when provided with conflicting instructions. \textit{PRIME} purposefully produces calibrated conflicts across response length, output format, and reasoning; classifying model responses with a deterministic behavioral taxonomy. We are evaluating five instruction tuned open weight LLMs in two distinct settings, balanced and naturally distributed. The conclusion we reach upon analysis is that conflict type is more significant in affecting behavior than model scale, and various failure modes across different categories of conflict. Our findings emphasize the value of developing conflict awareness and suggest ability of LLM to follow instructions cannot be assessed through isolated constraints alone.

Machine-translated benchmarks are widely used to assess the multilingual capabilities of large language models (LLMs), yet translation errors in these benchmarks remain underexplored, raising concerns about the reliability and comparability of multilingual evaluation. We address two practical gaps: (i) how well automatic MQM-style error spans from LLM judges and a span-aware QE baseline (xCOMET-XXL) match expert human span annotations on benchmark translations, and (ii) how strongly translation errors (as opposed to source-side issues in the English original) explain accuracy drops on translated benchmarks. We find that span agreement is non-trivial on naturally occurring benchmark translations, and that target-side translation errors are consistently associated with measurable, percentage-point drops in translated accuracy even after controlling for English correctness and source-side anomalies.

In this paper we present an active, constantly updated AI benchmark which measures the integrity of frontier language models against being co-opted for use by authoritarian state "information operations": intentional, coordinated activities by one state to influence public opinion and information ecosystems in another state. These information operations are a well documented, persistent threat against contemporary democracy. Our benchmark is based on real examples from over 2,100 information operations drawn from a live monitoring pipeline which tracks online information assets with links to authoritarian regimes. Alongside this paper, we also release a companion website that updates the benchmark weekly with new claims. The dynamic nature of this public facing benchmark makes it resistant to saturation. In the benchmark, we test 17 models from 8 providers across four prompt framings. We find that most models can be co-opted for information operations at least some of the time. Integrity scores, defined as the share of judged responses in which the model neither preserved nor amplified the claim, range from 9.3% to 91%, an 81.7-percentage-point spread not explained by model size. Models approach participation in information operations in a variety of ways. Some models fabricate details and produce output more harmful than the original input claim; others make claims less harmful even while complying and producing some output. Fact-checking rates vary from 3.2% to 80.8%. Integrity against information operations is at least partly related to refusal to produce content even for benign claims, illustrating the challenge of balancing model usability with safety. Overall, our results show the potential for contemporary information operations to be substantially aided by frontier AI models.

Source code and its accompanying comments are complementary yet naturally aligned modalities-code encodes structural logic while comments capture developer intent. However, existing vulnerability detection methods mostly rely on single-modality code representations, overlooking the complementary semantic information embedded in comments and thus limiting their generalization across complex code structures and logical relationships. To address this, we propose MultiVul, a multimodal contrastive framework that aligns code and comment representations through dual similarity learning and consistency regularization, augmented with diverse code-text pairs to improve robustness. Experiments on widely adopted DiverseVul and Devign datasets across four large language models (LLMs) (i.e., DeepSeek-Coder-6.7B, Qwen2.5-Coder-7B, StarCoder2-7B, and CodeLlama-7B) show that MultiVul achieves up to 27.07% F1 improvement over prompting-based methods and 13.37% over code-only Fine-Tuning, while maintaining comparable inference efficiency.

Despite the remarkable capabilities of Multimodal Large Language Models (MLLMs), they still suffer from visual fading in long-context scenarios. Specifically, the attention to visual tokens diminishes as the text sequence lengthens, leading to text generation detached from visual constraints. We attribute this degradation to the inherent inductive bias of Multimodal RoPE, which penalizes inter-modal attention as the distance between visual and text tokens increases. To address this, we propose inter-modal Distance Invariant Position Encoding (DIPE), a simple but effective mechanism that disentangles position encoding based on modality interactions. DIPE retains the natural relative positioning for intra-modal interactions to preserve local structure, while enforcing an anchored perceptual proximity for inter-modal interactions. This strategy effectively mitigates the inter-modal distance-based penalty, ensuring that visual signals remain perceptually consistent regardless of the context length. Experimental results demonstrate that by integrating DIPE with Multimodal RoPE, the model maintains stable visual grounding in long-context scenarios, significantly alleviating visual fading while preserving performance on standard short-context benchmarks. Code is available at https://github.com/lchen1019/DIPE.