Search research

Multi-step reasoning with Chain-of-Thought (CoT) prompting remains fragile: logical errors or hallucinations in early steps silently propagate, producing confident but incorrect conclusions. This paper presents VeryTrace, a zero-shot verification-and-repair framework that formalizes natural-language reasoning traces into a structured, compilable representation. VeryTrace introduces a Domain-Specific Language (DSL) that (i) makes step dependencies explicit, (ii) mechanizes quantitative content as executable expressions, and (iii) structures semantic inferences via deduction schemas. Our hybrid verifier combines deterministic checks for computational correctness, dependency resolution, and constraint satisfaction with targeted LLM audits for non-mechanizable semantic judgments, enabling step-level error localization and repair. Across three diverse domains-competition mathematics (AIME 2025), robotics planning (LLM-BabyBench), and kinship reasoning (CLUTRR), VeryTrace improves accuracy over zero-shot baselines on state-of-the-art LLMs without requiring domain-specific training or in-context examples, demonstrating that formalized trace verification achieves both precision and generalization.

Many recent vision-language-action (VLA) policies adopt an imagine-then-act design. A world-action model (WAM) first imagines a short future as a latent trajectory z~, on which the action is then conditioned. We identify this trusted imagination, rather than the reactive policy, as the exposed attack surface. A downstream oracle, such as a safety gate, a visual model-predictive-control (MPC) planner, or an imagine-then-check verifier, consumes z~ as a prediction of the future. The robustness of the policy therefore does not entail the robustness of systems that rely on the WAM. The underlying phenomenon is an asymmetry. Corrupting the imagination is easy, since it requires only displacing z~ from its natural-future manifold. Steering it precisely is hard, since it must reach a specified on-manifold target. We adopt a capability-based threat model with an L-infinity-bounded observation perturbation. The attacker applies projected gradient descent through the fully differentiable observation-to-imagination map. The same off-manifold property motivates a parameter-free denoiser detector. We evaluate three targets: RynnVLA-002, LingBot-VA, and LaDi-WM. Untargeted corruption is roughly 60x stronger than random and is detected at AUC 1.0. Targeted control remains bounded. An adaptive attacker evades detection only by forgoing corruption. The reactive policy remains robust to corrupted imagination. A native imagination-driven MPC, however, exhibits the first adversary-specific task failure (at epsilon=0.01, success 0.70 versus 0.05; Fisher p < 10^-4).

Generative AI tools provide novice programmers with instant, personalized support, but also raise concerns about whether AI use supports or bypasses students' regulation of problem-solving. Existing work has largely focused on correctness, usability, or overall usage frequency, with less attention to how student--AI help-seeking unfolds. This study addresses this gap by analyzing AI-assisted help-seeking trajectories in university-level programming. Using an SRL-informed analytical framework that links prompt-level help-seeking codes to conceptual, implementation, debugging, and reflective forms of support, we analyzed 1,290 task-specific student prompts linked to 17,190 code submissions from 71 students in introductory Python programming courses. Specifically, we examined how help-seeking interactions were structured across turns and attempts, and how trajectory patterns related to task scores and the number of code submissions. Results indicate that many students primarily used AI for reactive troubleshooting rather than for planned, self-regulated problem-solving. Although trajectory patterns were not associated with significant differences in task scores, they differed substantially in the number of code submissions required. These findings suggest that the educational significance of AI support lies not only in whether students use AI, but in how their help-seeking trajectories develop during programming problem-solving.

There exist numerous tutor training platforms. However, few provide AI-driven training and evaluation for human tutors based on real-life performance. We present an AI-driven system that assesses both open responses during training and authentic real-life tutoring. Unlike platforms that only assess learning through online training or simulations, our system utilizes Generative AI (Gemini-2.5-pro) to analyze transcriptions of authentic tutoring, measuring the transfer of tutor skills to real-life application. Human tutors instructing students remotely in math (N=86) completed six scenario-based lessons, averaging a significant 7.4% learning gain. Using mixed-effects models across 405 session-to-lesson pairs, we found that training performance significantly predicted real-life transcript scores with an effect size of 0.25 SD. Model comparison (AIC/BIC) indicated averaging open response and multiple choice performance during training predicted real-life tutor performance best, although open responses were comparatively more predictive. Exploratory analysis showed that after training, tutors were significantly more likely to encounter pedagogical opportunities to apply their skills (61.1% to 68.9%) and demonstrated higher execution quality within those opportunities (65.5% to 68.1%). Interrupted time series analysis suggested that these tutor improvements were part of a gradual trend over time rather than an immediate intervention effect of training. We illustrate an AI-driven method to link tutor training with real-life assessment. In doing so, we contribute open datasets, AI prompts, and scoring rubrics to support transparency and reproducibility.

Post-training pipelines that combine supervised fine-tuning (SFT) with reinforcement learning (RL) have emerged as the key recipe for transforming large language models (LLMs) into robust reasoners. We argue that this combined success is driven by compositional generalization, which we formalize through a hierarchical latent selection model. In this framework, reasoning traces are generated by a cascade of discrete latent selection variables corresponding to reusable atomic modules, including both skills (local operations) and routing mechanisms (how intermediate information is selected, reused, and composed). Within this model, we theoretically show that SFT and RL play asymmetric, complementary roles: SFT supplies the raw module materials in compositional traces, and RL decomposes those traces to identify the latent atomic modules and enable compositional generalization. We design controlled experiments to validate this theory. Our results demonstrate that RL can extract atomic modules from compound traces supplied by SFT and recombine them to solve new configurations. Moreover, we find that training on compound traces yields stronger generalization than training on isolated atomic modules. Finally, we investigate the relationship between SFT and RL data and identify an effective protocol in which SFT ensures coverage of all atomic modules through compositional traces, while RL focuses on novel compositions outside the SFT support to drive exploration.

Spiking neural networks (SNNs) are promising for energy-efficient inference, and time-to-first-spike (TTFS) coding is especially attractive because each neuron fires at most once. In practice, however, this benefit is often reduced by the cost of computing a temporal decay term and multiplying it by the synaptic weight. We address this issue by turning a physical hardware "bug," the natural signal decay in optoelectronic devices, into the main computation of TTFS, named Otters++. Specifically, we use the measured decay of a custom In$_2$O$_3$ optoelectronic synapse to directly realize the TTFS temporal term, removing the need for explicit digital decay computation. To scale this idea to Transformer models, we establish a layer-wise functional equivalence between the Otters++ and a quantized neural network (QNN), and develop a hybrid training method that uses device-faithful SNN computation in the forward pass and QNN straight-through gradients through the equivalent QNN path in the backward pass, together with model distillation. This avoids differentiation through discrete first-spike events and reduces the over-sparsity problem in direct TTFS-SNN training. We further make training aware of measured device noise by sampling run-to-run variation, and refine the system-level energy model by accounting for device sharing and multi-hop communication. On GLUE dataset, Otters++ improves the average score to 84.17% while maintaining a clear energy advantage over prior spiking Transformer baselines. These results show that physically grounded TTFS computing can be efficient, trainable, and robust under realistic hardware effects.

Reasoning models produce long chain-of-thought traces that are costly to distill and encourage verbose student outputs. We study post-hoc compression of such traces before knowledge distillation. Two teachers, Qwen3.5-397B-A17B and gpt-oss-120B, generate about 283k correct traces each; two instruction-tuned models then compress them to 8.6-21.0% of their original character length. Across a 48-run main grid plus seven Qwen-teacher truncation ablations, compressed traces reduce training tokens to 12-30% of raw, speed up training by 2.0-7.6x, and shorten inference outputs by 3-19x with smaller reductions under the shorter gpt-oss teacher. However, raw traces retain the highest downstream accuracy at every scale and for both teachers. A length-matched raw-trace truncation ablation shows that compression is not merely benefiting from a smaller token budget: model-compressed traces usually beat or match naive truncation, especially for smaller students, while maintaining shorter inference outputs. Overall, reasoning-trace compression offers an accuracy-efficiency trade-off rather than a free improvement: students retain up to 96% of raw-trace accuracy while gaining up to 18x higher per-token efficiency, and at the 0.8B scale under LoRA compressed traces narrow the raw-vs-compressed gap but do not exceed raw.

When post-trained language models fail on reasoning problems, the common test-time-scaling response is to spend more compute on additional attempts, and the failed traces play no further role. We argue this discards a crucial signal; some failures come from unlucky sampling, where more rollouts help, while others are structural and resist resampling regardless of budget. We propose that failed traces encode recoverability structure: the inference-time signature of which test-time interventions can rescue a given failure. Three problem-level trajectory features, derived from the structure of available interventions, recover this structure from the distributional signature of failed rollouts, not their text. They cluster failures into stable regimes, characterize the failure topography of different post-training methods ($84.3{\pm}4.3\%$ accuracy, $+20\%$ over a majority-class baseline), and support a training-free routing rule that lifts rescue by $+12.2\%$ on the deployment-relevant Steerable-Hard subset (failures where retry is insufficient and a bounded intervention is reachable). The features and the routing rule transfer across two cross-family probes. The same three features thus convert failed traces from discarded data into a diagnostic object, supporting test-time routing and post-training analysis without training-time or weight-space access.

Multi-agent systems are commonly designed to reduce disagreement through voting, consensus protocols, debate, or fault-tolerant aggregation. We argue that this objective is insufficient for value-laden tasks, where disagreement may reflect genuine normative uncertainty rather than agent error. Building on prior work on reasoning-trace disagreement in human-AI collaborative moderation, we propose a knowledge-representation layer in which reasoning traces and agent decisions are abstracted into symbolic disagreement states. Given agents producing explicit reasoning traces and binary decisions, we distinguish four states according to reasoning similarity and conclusion agreement: convergent agreement, divergent agreement, convergent disagreement and divergent disagreement. These states support defeasible strategic routing rules. We instantiate the framework in content moderation and argue that disagreement-aware routing provides a bridge between sub-symbolic LLM deliberation and symbolic knowledge representation for multi-agent strategic reasoning.

Large language models (LLMs) offer a promising approach to machine translation (MT) for extremely low-resource languages by incorporating linguistic resources through in-context learning. However, LLMs often struggle to apply grammatical information effectively during translation. Inspired by recent progress in chain-of-thought reasoning, we investigate whether low-resource MT can benefit from structured intermediate steps of linguistic analysis and grammatical reasoning. We propose a pipeline for automatically generating step-by-step linguistic reasoning traces from Universal Dependencies treebanks, dictionaries, and grammar-rule banks. We evaluate these traces in three settings: in-context learning (ICL), supervised fine-tuning (SFT), and reinforcement fine-tuning (RFT), on Xibe and Chintang as test cases. Our results show that linguistic reasoning traces are most effective as inference-time guidance: in ICL, reliable sentence-specific traces substantially improve translation performance across most models, languages, and metrics. In contrast, using the linguistic reasoning traces as training data yields smaller and less consistent gains, as models learn the trace format but often generate erroneous content. These findings suggest that LLMs can leverage grammatical information for low-resource MT when given reliable linguistic analyses, while learning to generate such analyses remains a major bottleneck.

Extracting reporting obligations from EU legislation is critical for assessing and reducing regulatory reporting burden. However, distinguishing reporting requirements from structurally similar provisions requires specialised legal understanding. Current legal NLP methods lack specialised datasets with clear guidelines and comparative evaluation of extraction paradigms and domain adaptation strategies. We curate EURO-5K, a corpus of sentence-level reporting obligations and challenging negative examples from 136 EU legislative acts. On this dataset, we train and compare discriminative token-classification models (BERT-style) and generative span-extraction models (LLMs), evaluating both full fine-tuning and parameter-efficient QLoRA against baselines (pattern and dependency-based extraction, few-shot prompting). Results show that fully fine-tuned generic and legal BERT models achieve similar performance (0.89 F1), while fine-tuned LLMs match encoder accuracy for sentence-level extraction. Legal pretraining offers only small gains for generative models. In contrast, it is clearly beneficial when adaptation capacity is constrained, as parameter-efficient tuning of Legal-BERT outperforms its generic counterpart. Learning curve analysis demonstrates that legal pretraining accelerates early learning with minimal data. All approaches converge around 3K samples with diminishing returns thereafter, validating dataset sufficiency. Cross-dataset evaluation on two external regulatory corpora shows that our models behave as specialised reporting obligation extractors rather than generic regulatory classifiers. We release EURO-5K, trained models, and an interactive demo with explainability visualizations and structured RDF export. These demonstrate that both paradigms and parameter-efficient training provide practical tools for regulatory compliance automation.

Reasoning traces have become a valuable form of learning signals for improving and transferring the capabilities of large language models. In particular, detailed traces can help distill reasoning behavior from stronger teacher models into weaker student models. The value of capability transfer has motivated many deployed systems with reasoning models to hide raw internal traces and expose at most summaries and answers to users. As a result, we ask whether such interface-level trace hiding prevents users from obtaining useful reasoning supervision through prompting. We study this question with Reasoning Exposure Prompting (REP), a lightweight in-context elicitation method that uses shadow-model-generated demonstrations wrapped in auxiliary code-like formats to raise user-visible reasoning traces from a victim model. Across the common reasoning dataset, different victim models, and different student model distillation, REP substantially increases similarity between exposed and REP-conditioned internal traces while preserving useful reasoning signals.

Language model reasoning traces are rarely all-or-nothing; they frequently contain valid intermediate steps before a critical error occurs. Existing uncertainty quantification methods typically certify final answers or entire responses, failing to provide statistical guarantees for the proportion of a sequential trace that can be safely retained. To address this, we introduce CROP (Conformal Reasoning Output Prefixes), a verifier-agnostic calibration procedure for clean-prefix certification. Given any step-level risk proxy, CROP selects a calibrated threshold and returns the longest contiguous prefix whose step risk proxies remain below it, routing the uncertified suffix for downstream review or repair. Assuming exchangeability, CROP rigorously controls the marginal probability that the returned prefix contains an annotated error. Across six process-labeled reasoning datasets, we demonstrate that standard step-level metrics such as AUROC do not fully capture prefix utility, suggesting verifiers should instead be evaluated by certified prefix length. Furthermore, CROP balances over- and under-withholding, improving downstream repair accuracy by preserving valid intermediate reasoning while discarding misleading suffixes. Ultimately, this work positions prefix certification as a rigorous, practical bridge between process supervision, abstention, and repair.

Long chain-of-thought (CoT) traces are widely used as supervision for reasoning-oriented LLM SFT, yet answer-correct traces can still lead to markedly different fine-tuning outcomes. We study post-conclusion continuation in answer-correct long-CoT data: a continuation where the answer appears sufficiently supported, but the trace continues with additional reasoning that remains in the supervised target. To test its training effect, we use a delete-only editor to construct answer-preserving suffix removal and compare CoT-based SFT on the original and processed traces. We observe improved SFT outcomes after removing the editor-identified post-conclusion continuation, suggesting that this continuation is harmful to training in our setting. We therefore refer to this empirically supported phenomenon as harmful continuation. Beyond this intervention, we further characterize the removed post-conclusion continuation through uncertainty and hidden-state progress. We observe persistent local uncertainty together with weakened terminal-directional progress, forming an uncertainty--geometry mismatch. Finally, we instantiate Harmful Continuation Cut (HCC), a lightweight boundary proxy that approximates the editor-identified post-conclusion continuation boundary.

Chain-of-thought traces from large reasoning models can span tens of thousands of tokens, yet we lack a vocabulary for describing their internal structure. Previous methods developed to analyze chain-of-thought traces are either too rigid or not expressive enough, failing to capture features across domains and models. To remedy this, we develop ReasonOps, an unsupervised, expressive method for annotating chain-of-thought traces, providing succinct universal operators. Using ReasonOps, we analyze 44,662 traces from 12 thinking LLMs spanning 6 families across 8 reasoning benchmarks and discover that they share a common compositional structure: 7 recurring reasoning operators -- discourse-level moves such as backtracking, inferring, and hypothesizing -- that emerge from unsupervised clustering of sentence-initial 3-token pivots. These operators appear across every model family and benchmark domain, confirmed by three independent LLM judges who classify held-out samples at 70 -76% accuracy. We analyze the structure of operators on easy vs. hard problems, revealing that reflective operators are more helpful on hard problems and harm performance on easy problems. Operator sequences are highly model-identifying: a classifier trained on operator distributions alone recovers the source model with macro-AUC, revealing that each model family has a distinctive reasoning fingerprint. Structural operator features predict within-problem answer correctness well above baselines. Classifiers built on these operators reach WP-AUC and on AIME specifically. ReasonOps further enables early quality estimation well before the trace completes: we predict at WP-AUC for only 50% of the trace. The ReasonOps pipeline is unsupervised and annotation-free, enabling deep insights into LLM reasoning traces as well as strong downstream results on model identification and correctness prediction.

Large Language Model interfaces are increasingly verbose, exposing intermediate reasoning traces alongside final answers. Traces are framed as transparency mechanisms, yet it is unclear how people use them to solve problems. We report a preregistered between-subjects study (N = 559) in which participants solved ten LSAT-style reasoning problems under one of three conditions: an Answer-only baseline, a Full-trace revealed before the answer, and a Summary-trace presented alongside the answer. Summaries preserved task performance at the no-trace baseline while significantly elevating trust and hedonic appeal, establishing that trace exposure shifts subjective appraisal of the interaction without bringing performance benefits. Under an open-weight reasoning model exposing verbose intermediate output, full traces additionally impaired performance relative to the answer-only baseline. Across all conditions, participants substantially overestimated their performance, and no trace format supported calibrated self-evaluation. Further analysis indicates that hedonic appeal, not trust, carries the indirect path to overestimation, consistent with a processing-fluency account. Reasoning traces are best understood as user-facing interface artifacts rather than transparent windows into model cognition, and calibration is unlikely to emerge from the traces themselves and may best be scaffolded by interactions that elicit users' own reasoning first.

Vision foundation models pretrained on web-scale data have recently shown strong transfer capabilities on many downstream tasks, but their effectiveness for industrial visual inspection remains unclear. Industrial data differ substantially from web-data and often require fine-grained dense prediction, raising the question of whether modern self-supervised pretraining can improve over the conventional transfer-learning paradigm based on supervised ImageNet initialization. In this work, we compare ConvNeXt backbones pretrained with supervised ImageNet classification or DINOv3 distillation, and relate them to the conventional ResNet-50 baseline. We evaluate semantic segmentation, instance segmentation, and object detection across four downstream datasets spanning RGB surface-defect inspection and X-ray defect detection. We further study both frozen and fully finetuned adaptation regimes. Our results show that DINOv3 offers no clear advantage in frozen transfer, but provides a stronger initialization after full finetuning on RGB tasks, yielding faster convergence and better final performance. Under X-ray modality shift, however, supervised ImageNet pretraining remains more effective in both frozen and finetuned settings. Overall, our findings suggest that modern vision foundation models are promising for supervised RGB industrial inspection, but their transferability is strongly conditioned by downstream adaptation and target modality.

We introduce Lens, a 3.8B-parameter T2I model that achieves performance competitive with, and in several cases surpassing, state-of-the-art models with more than 6B parameters across various benchmarks, while requiring significantly less training compute. For example, Lens requires only about 19.3% of the training compute used by Z-Image. The training efficiency of Lens stems from two key strategies beyond its compact model size. First, we maximize data information density per training batch by (i) training on Lens-800M, a dataset of 800M densely captioned image-text pairs whose captions are generated by GPT-4.1 and contain approximately 109 words on average, providing richer semantic supervision than conventional short captions, and (ii) constructing each batch from images with multiple resolutions and diverse aspect ratios, thereby enlarging the effective visual coverage of each optimization step. Second, we improve convergence speed through careful architectural choices, including adopting a semantic VAE that provides better latent representations and employing a strong language encoder that accelerates optimization while enabling multilingual generalization from English-only training data. After pre-training, we apply RL with taxonomy-driven prompts (Lens-RL-8K) and structured reward rubrics to suppress artifacts and improve visual quality, a reasoner module with training-free system prompt search to better align user requests with the model, and distillation-based acceleration for 4-step inference. Through efficient training and systematic optimization, Lens generalizes to arbitrary aspect ratios from 1:2 to 2:1 and resolutions up to 1440^2, and supports prompts in several commonly used languages. Thanks to its compact size, Lens generates a 1024^2 image in 3.15 seconds on a single NVIDIA H100 GPU, while its distilled turbo version performs 4-step generation in 0.84 seconds.

Explicit reasoning models are trained to produce intermediate reasoning traces before final answers, but downstream fine-tuning is often performed on ordinary instruction-response data that contains no such traces. We show that this mismatch can induce reasoning-trace collapse: a fine-tuned model continues to produce plausible final answers while losing the structurally valid explicit reasoning traces that made it a reasoning model in the first place. We introduce a structural evaluation framework that separates answer correctness from reasoning-trace validity, measuring valid, empty, missing, and truncated reasoning alongside reasoning-conditioned task performance. Using this framework, we study four open-weight reasoning models and find that standard supervised fine-tuning can rapidly suppress valid reasoning traces, and that answer-only metrics can substantially obscure this failure: in several settings, performance conditional on valid reasoning remains high while the rate of valid reasoning falls sharply. We further show that simple loss-masking strategies can substantially mitigate collapse without requiring teacher-generated reasoning traces. These results suggest that evaluations of fine-tuned reasoning models should report structural reasoning reliability metrics in addition to final-answer performance, especially when adaptation data does not contain explicit reasoning traces.

ANN-to-SNN conversion offers a practical, training-free route to spiking large language models. However, current pipelines primarily focus on spike-driven realizations for Transformer linear-algebra operations, while providing limited support for key nonlinear operators. This gap limits compatibility with neuromorphic-style execution constraints, where such nonlinearities typically require division, exponentiation, or norm computations that are not naturally supported by standard leaky integrate-and-fire dynamics. To solve this problem, we propose a plug-and-play framework that implements spike-friendly approximations for Transformer nonlinearities and integrates into existing ANN-to-SNN pipelines. Our method decomposes these nonlinear computations into three recurring primitives -- division, exponentiation, and $\ell_2$ norms -- and realizes them via population computation using LIF neuron groups, combined with lightweight bit-shift scaling to avoid floating-point arithmetic. By composing these primitives as modular operator blocks, our framework supports common Transformer nonlinearities (e.g., Softmax, SiLU, and normalization) without any fine-tuning. Experiments on a range of LLMs Transformers show that selectively replacing the targeted nonlinear operators incurs less than a $1\%$ accuracy drop across all evaluated tasks.

Methods: Nine SSL methods spanning four pretext-task families were pretrained from scratch using the same 10{,}412 3D CT scans (1.89~M 2D axial slices) covering varied disease sites. The pretrained Swin Transformer encoder from each method was integrated into a SwinUNETR-style segmentation network (Swin encoder with a 3D CNN decoder and skip connections) and fine-tuned on nine public segmentation tasks of varying complexity, including large abdominal organs, head-and-neck structures, and tumors from CT and MRI. Performance was assessed using Dice similarity coefficient (DSC). Fine-tuning convergence speed, transferability across modalities (CT-to-MRI), and feature-reuse patterns between few- and many-shot fine tuning were further analyzed using centered kernel alignment. Results: Self-distilled masked image transformer (SMIT), which combines masked image modeling (MIM) with local and global self-distillation, achieved the highest overall segmentation accuracy across the nine tasks, the fastest fine-tuning convergence, and the smallest few-shot-to-many-shot performance gap, indicating the strongest data efficiency. SMIT also showed the most consistent feature-reuse patterns between few- and many-shot fine tuning. MIM-based SimMIM and self-distillation methods (DINO, iBOT) outperformed contrastive learning and rotation prediction, which rely on image-level global representations. Differences between SSL methods were largest in the few-shot setting and narrowed as the size of the labeled fine-tuning dataset increased, indicating that the choice of SSL pretraining matters most under limited annotation budgets.

Binary function classifiers play a crucial role in maintaining the security and integrity of software systems by detecting malicious code and unauthorized modifications. However, machine learning-based classifiers are vulnerable to adversarial attacks that can evade detection. In this study, we present Kelpie, a novel framework for executing mimicry attacks, a stronger type of targeted evasion attacks, on binary function classifiers in a black-box, zero-query setting. Unlike previous approaches that rely on querying the target classifier to refine untargeted evasion attacks, Kelpie leverages code transformations that preserve the functionality of malicious payloads while causing them to be misclassified as we want. Through extensive experimentation, we demonstrate that Kelpie can successfully execute mimicry attacks against six state-of-the-art binary function classifiers representing different model architectures without requiring direct interaction with them. We further validate our approach with a practical demonstration, involving a keylogger and a wiper concealed within benign-looking functions embedded in an application. This work, to our best knowledge, is the first to demonstrate such a mimicry attack in a black-box, zero-query context, raising important questions about the reliability and security of existing machine learning-based binary function classifiers.

Evaluations of unlearning on reasoning models sometimes show a bypass pattern. The answer side looks unlearned, but the model's own thinking trace keeps emitting the forgotten content, and the gap is taken as evidence that the weights still remember. We audit this reading on DeepSeek-R1-Distill-Qwen-7B with LoRA-memorized fictional authors and NPO unlearning, conditioned on a six-token canary head. On one seed, swapping the thinking trace for a short non-canary prefill on the same weights drops the answer rate by as much as the bypass gap itself, whether the prefill mimics the training template or not. On a second seed the bypass gap shrinks rather than vanishing, and the prefill swap reverses direction and brings the answer rate to ceiling. A positive parser-split bypass gap thus does not by itself identify hidden weight-level memorization, and does not rule it out either. On a different distillate the same metric flips sign because the parser cannot find the closing tag. We recommend a decode-time template swap as a cheap sanity check alongside the canonical audit.

Training large-scale deep neural networks (DNNs) is resource-intensive, making model compression a practical necessity. The widely accepted ''learning as compression'' hypothesis posits that training induces structure in network weights, which enables compression. Measuring this structure through Kolmogorov-Chaitin-Solomonoff (KCS) complexity is appealing, but existing estimators based on the Coding Theorem Method (CTM) and the Block Decomposition Method (BDM) are limited to small binary objects and do not scale to modern DNNs. We introduce the Quantized Block Decomposition method (QuBD), which extends algorithmic complexity estimation to any $k$-ary object. QuBD first quantizes the network weights to a finite alphabet, then estimates the KCS complexity by aggregating per bit-plane CTM estimates. We show theoretically that QuBD yields a strictly tighter estimation gap with respect to true KCS complexity than binarization-based methods. Using QuBD, we study how the algorithmic complexity of neural network weights evolves during training, showing that it decreases as models learn, scales with data budget, increases during overfitting, follows the delayed generalization observed during grokking, and correlates with generalization performance. We further show that algorithmic information resides predominantly in the most significant bit-planes, which can serve as a practical diagnostic for determining appropriate post-training quantization levels. This work offers novel insights into learning mechanisms in DNNs by providing the first scalable, tractable estimates of KCS complexity for large, non-binary objects such as DNN weights.

Language models often generate long chain-of-thought traces, but it remains unclear how much of this reasoning is necessary for preserving the final prediction. We study this through the lens of overcomplete reasoning traces: generated traces that contain more intermediate steps than are needed to support the model's answer. We define the minimal core as the smallest subset of steps that preserves either the final answer or predictive distribution, and introduce metrics for compression ratio, redundancy mass, step necessity, and necessity concentration. Across six deliberative reasoning benchmarks spanning arithmetic, competition mathematics, expert scientific reasoning, and commonsense multi-hop QA, we find substantial overcompleteness: on average, 46% of steps are removable under greedy minimal-core extraction while preserving the original answer in 86% of cases. We also find that predictive support is concentrated: the top three steps account for 65% of measured necessity mass on average. Beyond compression, minimal cores expose a cleaner geometry of reasoning: compared with full traces, they improve correct-incorrect trace separation by 11 points, reduce estimated intrinsic dimensionality by 34%, and transfer across model families with 85% off-diagonal answer retention. Theoretically, we establish existence of minimal sufficient subsets, local irreducibility guarantees for greedy elimination, and certificates of overcompleteness and sparse necessity. Together, these results suggest that full reasoning traces are often verbose and overcomplete, while minimal cores isolate the effective support underlying language-model predictions.

Chain-of-thought (CoT) traces are increasingly used both to improve language model capability and to audit model behavior, implicitly assuming that the visible trace remains synchronized with the computation that determines the answer. We test this assumption with a step-level Detect-Classify-Compare framework built around an answer-commitment proxy that is cross-validated with Patchscopes, tuned-lens probes, and causal direction ablation. Across nine models and seven reasoning benchmarks, latent commitment and explicit answer arrival align on only 61.9% of steps on average. The dominant mismatch pattern is confabulated continuation: 58.0% of detected mismatch events occur after the answer-commitment proxy has already stabilized while the trace continues producing deliberative-looking text, and a vacuousness analysis shows that the committed answer does not change during these steps. In architecture-matched Qwen2.5/DeepSeek-R1-Distill comparisons, the reasoning pipeline changes failure composition more than aggregate alignment, most clearly at 32B where confabulated steps decrease as contradictory states increase. Lower step-level alignment is also associated with larger CoT utility, suggesting that the settings that benefit most from CoT are often the least temporally faithful. Paired truncation and a complementary donor-corruption test further indicate that much post-commitment text is not load-bearing for the final answer. These findings suggest that CoT can remain useful while still being an unreliable report of when the answer was formed.

Political and social identities structure how people evaluate political information, a finding decades deep in political science and routinely discarded by computational tools that often produce single scores that treat a piece of text, an image, or a video as if it means the same thing to everyone. This paper shows that it does not, and that the difference is consequential. To address this problem, I develop the Perspectivist Visual Political Sentiment (PVPS) classifier, which learns from approximately 82,000 evaluations by 5,575 U.S. adults to predict how audiences defined by political and social identities will evaluate the same image. Unlike standard tools that average systematic disagreement away, PVPS preserves it, returning an evaluative profile that records who agrees, who diverges, and along which identity lines. Applied to several influential studies of visual sentiment, PVPS shows that perceived violence in protest imagery and the emotional mechanisms behind protest image engagement both change substantively once audience identity is taken into account. It follows that what a political image conveys is a moving target, and measuring it requires knowing whom it is moving.

Obtaining an accurate short-term forecasting for heat demand is an essential part of operating district heating networks cost-efficient and reliable. Heat consumption time series at the building level are highly dependent on exogenous variables such as outdoor temperature and individual usage patterns, making forecasting in this context a challenging task. Thus, this paper benchmarks novel Transformer-based and xLSTM architectures for short-term heat-demand forecasting. Using hourly data from 25 German buildings (2017-2025), we compare three-hour and 24-hour forecasting horizons relevant for intraday control and day-ahead scheduling. We establish a multi-building benchmark that tests whether models trained on pooled, heterogeneous building data are able to generalize across diverse building stock. The results show that the xLSTM achieves the lowest RMSE (19.88 kWh for three-hour, 21.47 kWh for 24-hour forecasts), while the Temporal Fusion Transformer attains the best MAE (9.16 kWh for three-hour forecasts). As xLSTMs and Transformers require long training times and have a huge number of trainable parameters, their sustainability remains questionable. Therefore, this paper further investigates the trade-off between predictive accuracy and computational resource demand of the evaluated forecasting models. The findings indicate that also low-parameter models like a traditional fully-connected network achieve good predictive results, highlighting that marginal accuracy gains of the novel prediction models come at substantial resource expense for this use case.

Spiking transformers have shown strong potential for neuromorphic vision, yet their token processing across multiple spiking steps still introduces substantial redundancy and inference cost. Existing token reduction methods mainly rely on response based cues, such as activation magnitude, firing statistics, or feature similarity. Although effective, these criteria do not explicitly characterize token importance from the perspective of temporally evolving class evidence. In spiking transformers, token representations are progressively formed across multiple spiking steps rather than determined at a single instant, suggesting that token importance should be evaluated not only by instantaneous responses but also by temporal uncertainty patterns. Our key observation is that tokens exhibit heterogeneous uncertainty trajectories over time, and that their temporally aggregated uncertainty statistics provide an effective cue for distinguishing informative tokens from redundant ones. Motivated by this, we propose Uncert, a training free and plug and play token importance estimation framework for spiking transformers. Specifically, Uncert models token wise class evidence with a Dirichlet distribution and summarizes each token temporal uncertainty using its mean and fluctuation across spiking steps, yielding an uncertainty aware importance score for token reduction during inference. Experiments on both static and neuromorphic benchmarks show that Uncert achieves favorable accuracy and efficiency tradeoffs, with the most consistent gains observed under token pruning. Further analysis reveals a clear empirical connection between temporal uncertainty patterns and token contribution, offering new insights into token dynamics in spiking transformers.

A standard technique for scaling inference-time reasoning is Self-Consistency, whereby multiple candidate answers are sampled from an LLM and the most common answer is selected. More recently, it has been shown that weighted majority voting (e.g. Confidence-Informed Self Consistency (CISC)), which assigns a confidence value to each candidate answer and chooses the answer with the largest accumulated score, tends to be more accurate on a wide range of popular benchmarks. In practice, weighted majority voting necessitates calling a critic LLM on each candidate's reasoning trace to produce the answer's confidence score. This secondary series of LLM calls greatly increases the overhead and cost of weighted majority voting, despite its potential performance benefits. To reduce this expense, we propose VecCISC, a lightweight, adaptive framework that uses a measure of semantic similarity to filter reasoning traces that are semantically equivalent to others, degenerate, or hallucinated, thus decreasing the number of candidate answers that must be evaluated by the critic. To ensure adequate experimental thoroughness, we evaluate VecCISC on five challenging, widely-adopted datasets spanning the domains of mathematics, chemistry, biology, commonsense reasoning, and the humanities. Our results demonstrate that VecCISC reduces the total token usage by 47%, while maintaining or exceeding the accuracy of CISC.