# Research Papers — 2026-02 · bundle page 194 of 210

> Full-text markdown of papers #9651–9700 of 10493 published in 2026-02, newest first. AI-readable mirrors of the full 10493-paper 2026-02 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-02/page/194
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/193.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/195.md)

### RANKVIDEO: Reasoning Reranking for Text-to-Video Retrieval

Authors: Tyler Skow, Alexander Martin, Benjamin Van Durme, Rama Chellappa, Reno Kriz
Published: 2026-02-02
Categories: cs.IR, cs.CV
arXiv: https://arxiv.org/abs/2602.02444v2

Reranking is a critical component of modern retrieval systems, which typically pair an efficient first-stage retriever with a more expressive model to refine results. While large reasoning models have driven rapid progress in text-centric reranking, reasoning-based reranking for video retrieval remains underexplored. To address this gap, we introduce RANKVIDEO, a reasoning-based reranker for video retrieval that explicitly reasons over query-video pairs using video content to assess relevance. RANKVIDEO is trained using a two-stage curriculum consisting of perception-grounded supervised fine-tuning followed by reranking training that combines pointwise, pairwise, and teacher confidence distillation objectives, and is supported by a data synthesis pipeline for constructing reasoning-intensive query-video pairs. Experiments on the large-scale MultiVENT 2.0 benchmark demonstrate that RANKVIDEO consistently improves retrieval performance within a two-stage framework, yielding an average improvement of 31% on nDCG@10 and outperforming text-only and vision-language reranking alternatives, while more efficient.

---

### Certain Head, Uncertain Tail: Expert-Sample for Test-Time Scaling in Fine-Grained MoE

Authors: Yuanteng Chen, Peisong Wang, Nanxin Zeng, Yuantian Shao, Shuang Qiu, Gang Li, Jing Liu, Jian Cheng
Published: 2026-02-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.02443v2

Test-time scaling improves LLM performance by generating multiple candidate solutions, yet token-level sampling requires temperature tuning that trades off diversity against stability. Fine-grained MoE, featuring hundreds of well-trained experts per layer and multi-expert activation per token, offers an unexplored alternative through its rich routing space. We empirically characterize fine-grained MoE routing and uncover an informative pattern: router scores exhibit a certain head of high-confidence experts followed by an uncertain tail of low-confidence candidates. While single-run greedy accuracy remains stable when fewer experts are activated, multi-sample pass@n degrades significantly-suggesting that the certain head governs core reasoning capability while the uncertain tail correlates with reasoning diversity. Motivated by these findings, we propose Expert-Sample, a training-free method that preserves high-confidence selections while injecting controlled stochasticity into the uncertain tail, enabling diverse generation without destabilizing outputs. Evaluated on multiple fine-grained MoE models across math, knowledge reasoning, and code tasks, Expert-Sample consistently improves pass@n and verification-based accuracy. On Qwen3-30B-A3B-Instruct evaluated on GPQA-Diamond with 32 parallel samples, pass@32 rises from 85.4% to 91.9%, and accuracy improves from 59.1% to 62.6% with Best-of-N verification.

---

### Large Language Models for Mental Health: A Multilingual Evaluation

Authors: Nishat Raihan, Sadiya Sayara Chowdhury Puspo, Ana-Maria Bucur, Stevie Chancellor, Marcos Zampieri
Published: 2026-02-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.02440v1

Large Language Models (LLMs) have remarkable capabilities across NLP tasks. However, their performance in multilingual contexts, especially within the mental health domain, has not been thoroughly explored. In this paper, we evaluate proprietary and open-source LLMs on eight mental health datasets in various languages, as well as their machine-translated (MT) counterparts. We compare LLM performance in zero-shot, few-shot, and fine-tuned settings against conventional NLP baselines that do not employ LLMs. In addition, we assess translation quality across language families and typologies to understand its influence on LLM performance. Proprietary LLMs and fine-tuned open-source LLMs achieve competitive F1 scores on several datasets, often surpassing state-of-the-art results. However, performance on MT data is generally lower, and the extent of this decline varies by language and typology. This variation highlights both the strengths of LLMs in handling mental health tasks in languages other than English and their limitations when translation quality introduces structural or lexical mismatches.

---

### Energy-Efficient Neuromorphic Computing for Edge AI: A Framework with Adaptive Spiking Neural Networks and Hardware-Aware Optimization

Authors: Olaf Yunus Laitinen Imanov, Derya Umut Kulali, Taner Yilmaz, Duygu Erisken, Rana Irem Turhan
Published: 2026-02-02
Categories: cs.NE, cs.ET, cs.LG
arXiv: https://arxiv.org/abs/2602.02439v1

Edge AI applications increasingly require ultra-low-power, low-latency inference. Neuromorphic computing based on event-driven spiking neural networks (SNNs) offers an attractive path, but practical deployment on resource-constrained devices is limited by training difficulty, hardware-mapping overheads, and sensitivity to temporal dynamics. We present NeuEdge, a framework that combines adaptive SNN models with hardware-aware optimization for edge deployment. NeuEdge uses a temporal coding scheme that blends rate and spike-timing patterns to reduce spike activity while preserving accuracy, and a hardware-aware training procedure that co-optimizes network structure and on-chip placement to improve utilization on neuromorphic processors. An adaptive threshold mechanism adjusts neuron excitability from input statistics, reducing energy consumption without degrading performance. Across standard vision and audio benchmarks, NeuEdge achieves 91-96% accuracy with up to 2.3 ms inference latency on edge hardware and an estimated 847 GOp/s/W energy efficiency. A case study on an autonomous-drone workload shows up to 312x energy savings relative to conventional deep neural networks while maintaining real-time operation.

---

### UniReason 1.0: A Unified Reasoning Framework for World Knowledge Aligned Image Generation and Editing

Authors: Dianyi Wang, Chaofan Ma, Feng Han, Size Wu, Wei Song, Yibin Wang, Zhixiong Zhang, Tianhang Wang, Siyuan Wang, Zhongyu Wei, Jiaqi Wang
Published: 2026-02-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.02437v4

Unified multimodal models often struggle with complex synthesis tasks that demand deep reasoning, and typically treat text-to-image generation and image editing as isolated capabilities rather than interconnected reasoning steps. To address this, we propose UniReason, a unified framework that harmonizes these two tasks through two complementary reasoning paradigms. We incorporate world knowledge-enhanced textual reasoning into generation to infer implicit knowledge, and leverage editing capabilities for fine-grained editing-like visual refinement to further correct visual errors via self-reflection. This approach unifies generation and editing within a shared architecture, mirroring the human cognitive process of planning followed by refinement. We support this framework by systematically constructing a large-scale reasoning-centric dataset (~300k samples) covering five major knowledge domains (e.g., cultural commonsense, physics, etc.) for textual reasoning, alongside an agent-generated corpus for visual refinement. Extensive experiments demonstrate that UniReason achieves advanced performance on reasoning-intensive benchmarks such as WISE, KrisBench and UniREditBench, while maintaining superior general synthesis capabilities.

---

### Maximizing Reliability with Bayesian Optimization

Authors: Jack M. Buckingham, Ivo Couckuyt, Juergen Branke
Published: 2026-02-02
Categories: cs.LG, math.OC, stat.ML
arXiv: https://arxiv.org/abs/2602.02432v1

Bayesian optimization (BO) is a popular, sample-efficient technique for expensive, black-box optimization. One such problem arising in manufacturing is that of maximizing the reliability, or equivalently minimizing the probability of a failure, of a design which is subject to random perturbations - a problem that can involve extremely rare failures ($P_\mathrm{fail} = 10^{-6}-10^{-8}$). In this work, we propose two BO methods based on Thompson sampling and knowledge gradient, the latter approximating the one-step Bayes-optimal policy for minimizing the logarithm of the failure probability. Both methods incorporate importance sampling to target extremely small failure probabilities. Empirical results show the proposed methods outperform existing methods in both extreme and non-extreme regimes.

---

### Full-Batch Gradient Descent Outperforms One-Pass SGD: Sample Complexity Separation in Single-Index Learning

Authors: Filip Kovačević, Hong Chang Ji, Denny Wu, Mahdi Soltanolkotabi, Marco Mondelli
Published: 2026-02-02
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.02431v2

It is folklore that reusing training data more than once can improve the statistical efficiency of gradient-based learning. While this phenomenon has been extensively studied in linear regression, the benefit of multi-pass gradient descent (GD, which reuses all the data) over one-pass stochastic gradient descent (online SGD, which uses each data point only once) is not well-understood in nonlinear and non-convex settings, except for a loss modification mechanism achieved by the first two passes on the data. In this work, we consider learning a $d$-dimensional single-index model with a quadratic activation, for which it is known that one-pass SGD requires $n\gtrsim d\log d$ samples to achieve weak recovery. We first show that this $\log d$ factor in the sample complexity persists for full-batch spherical GD on the correlation loss; however, by simply truncating the activation, full-batch GD exhibits a favorable optimization landscape at $n \simeq d$ samples, thereby outperforming one-pass SGD (with the same activation) in statistical efficiency. We complement this result with a trajectory analysis of full-batch GD on the squared loss from small initialization, showing that $n \gtrsim d$ samples and $T \gtrsim\log d$ gradient steps suffice to achieve strong (exact) recovery.

---

### Embedding Perturbation may Better Reflect Intermediate-Step Uncertainty in LLM Reasoning

Authors: Qihao Wen, Jiahao Wang, Yang Nan, Pengfei He, Ravi Tandon, Han Xu
Published: 2026-02-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.02427v3

Large Language Models (LLMs) have achieved significant breakthroughs across various domains, but they can still produce unreliable or misleading outputs. For responsible LLM applications, uncertainty quantification techniques are used to estimate a model's uncertainty about its outputs, indicating the likelihood that those outputs may be problematic. For LLM reasoning tasks, it is essential to estimate uncertainty not only in the final answer but also in the intermediate reasoning process, particularly to identify where uncertainty arises. Such information may enable more fine-grained and targeted interventions during inference. In this study, we investigate which metrics can effectively localize uncertain places within an LLM reasoning trajectory. Our study reveals that uncertain intermediate continuations are more likely to occur at tokens that are highly sensitive to perturbations in the embeddings of preceding tokens. In our experiments, we show that such perturbation-based metrics achieve stronger performance in localizing uncertain intermediate steps than baseline methods, including probability-based, sampling-based, and Bayesian-based approaches. Meanwhile, our proposed metrics also enjoy good simplicity and efficiency.

---

### Embedding Perturbation may Better Reflect Intermediate-Step Uncertainty in LLM Reasoning

Authors: Qihao Wen, Jiahao Wang, Yang Nan, Pengfei He, Ravi Tandon, Han Xu
Published: 2026-02-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.02427v2

Large language Models (LLMs) have achieved significant breakthroughs across diverse domains; however, they can still produce unreliable or misleading outputs. For responsible LLM application, Uncertainty Quantification (UQ) techniques are used to estimate a model's uncertainty about its outputs, indicating the likelihood that those outputs may be problematic. For LLM reasoning tasks, it is essential to estimate the uncertainty not only for the final answer, but also for the intermediate steps of the reasoning, as this can enable more fine-grained and targeted interventions. In this study, we explore what UQ metrics better reflect the LLM's "intermediate uncertainty" during reasoning. Our study reveals that an LLM's incorrect reasoning steps tend to contain tokens which are highly sensitive to the perturbations on the preceding token embeddings, indicating the model's uncertainty among multiple competing continuations. In this way, uncertain (possibly incorrect) intermediate steps can be readily identified using this sensitivity score as guidance in practice. In our experiments, we show such perturbation-based metrics achieve stronger uncertainty quantification performance compared with baselines including probability-based, sampling-based and Bayesian-based methods. Meanwhile, such metrics also enjoy good simplicity and efficiency.

---

### SelvaMask: Segmenting Trees in Tropical Forests and Beyond

Authors: Simon-Olivier Duguay, Hugo Baudchon, Etienne Laliberté, Helene Muller-Landau, Gonzalo Rivas-Torres, Arthur Ouaknine
Published: 2026-02-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.02426v1

Tropical forests harbor most of the planet's tree biodiversity and are critical to global ecological balance. Canopy trees in particular play a disproportionate role in carbon storage and functioning of these ecosystems. Studying canopy trees at scale requires accurate delineation of individual tree crowns, typically performed using high-resolution aerial imagery. Despite advances in transformer-based models for individual tree crown segmentation, performance remains low in most forests, especially tropical ones. To this end, we introduce SelvaMask, a new tropical dataset containing over 8,800 manually delineated tree crowns across three Neotropical forest sites in Panama, Brazil, and Ecuador. SelvaMask features comprehensive annotations, including an inter-annotator agreement evaluation, capturing the dense structure of tropical forests and highlighting the difficulty of the task. Leveraging this benchmark, we propose a modular detection-segmentation pipeline that adapts vision foundation models (VFMs), using domain-specific detection-prompter. Our approach reaches state-of-the-art performance, outperforming both zero-shot generalist models and fully supervised end-to-end methods in dense tropical forests. We validate these gains on external tropical and temperate datasets, demonstrating that SelvaMask serves as both a challenging benchmark and a key enabler for generalized forest monitoring. Our code and dataset will be released publicly.

---

### Repurposing Protein Language Models for Latent Flow-Based Fitness Optimization

Authors: Amaru Caceres Arroyo, Lea Bogensperger, Ahmed Allam, Michael Krauthammer, Konrad Schindler, Dominik Narnhofer
Published: 2026-02-02
Categories: cs.LG, q-bio.QM
arXiv: https://arxiv.org/abs/2602.02425v1

Protein fitness optimization is challenged by a vast combinatorial landscape where high-fitness variants are extremely sparse. Many current methods either underperform or require computationally expensive gradient-based sampling. We present CHASE, a framework that repurposes the evolutionary knowledge of pretrained protein language models by compressing their embeddings into a compact latent space. By training a conditional flow-matching model with classifier-free guidance, we enable the direct generation of high-fitness variants without predictor-based guidance during the ODE sampling steps. CHASE achieves state-of-the-art performance on AAV and GFP protein design benchmarks. Finally, we show that bootstrapping with synthetic data can further enhance performance in data-constrained settings.

---

### Poly-attention: a general scheme for higher-order self-attention

Authors: Sayak Chakrabarti, Toniann Pitassi, Josh Alman
Published: 2026-02-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.02422v2

The self-attention mechanism, at the heart of the Transformer model, is able to effectively model pairwise interactions between tokens. However, numerous recent works have shown that it is unable to perform basic tasks involving detecting triples of correlated tokens, or compositional tasks where multiple input tokens need to be referenced to generate a result. Some higher-dimensional alternatives to self-attention have been proposed to address this, including higher-order attention and Strassen attention, which can perform some of these polyadic tasks in exchange for slower, superquadratic running times. In this work, we define a vast class of generalizations of self-attention, which we call poly-attention mechanisms. Our mechanisms can incorporate arbitrary higher-order (tensor) computations as well as arbitrary relationship structures between the input tokens, and they include the aforementioned alternatives as special cases. We then systematically study their computational complexity and representational strength, including giving new algorithms and matching complexity-theoretic lower bounds on the time complexity of computing the attention matrix exactly as well as approximately, and tightly determining which polyadic tasks they can each perform. Our results give interesting trade-offs between different desiderata for these mechanisms, including a tight relationship between how expressive a mechanism is, and how large the coefficients in the model may be so that the mechanism can be approximated in almost-linear time. Notably, we give a new attention mechanism which can be computed exactly in quadratic time, and which can perform function composition for any fixed number of functions. Prior mechanisms, even for just composing two functions, could only be computed in superquadratic time, and our new lower bounds show that faster algorithms for them are not possible.

---

### Poly-attention: a general scheme for higher-order self-attention

Authors: Sayak Chakrabarti, Toniann Pitassi, Josh Alman
Published: 2026-02-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.02422v1

The self-attention mechanism, at the heart of the Transformer model, is able to effectively model pairwise interactions between tokens. However, numerous recent works have shown that it is unable to perform basic tasks involving detecting triples of correlated tokens, or compositional tasks where multiple input tokens need to be referenced to generate a result. Some higher-dimensional alternatives to self-attention have been proposed to address this, including higher-order attention and Strassen attention, which can perform some of these polyadic tasks in exchange for slower, superquadratic running times. In this work, we define a vast class of generalizations of self-attention, which we call poly-attention mechanisms. Our mechanisms can incorporate arbitrary higher-order (tensor) computations as well as arbitrary relationship structures between the input tokens, and they include the aforementioned alternatives as special cases. We then systematically study their computational complexity and representational strength, including giving new algorithms and matching complexity-theoretic lower bounds on the time complexity of computing the attention matrix exactly as well as approximately, and tightly determining which polyadic tasks they can each perform. Our results give interesting trade-offs between different desiderata for these mechanisms, including a tight relationship between how expressive a mechanism is, and how large the coefficients in the model may be so that the mechanism can be approximated in almost-linear time. Notably, we give a new attention mechanism which can be computed exactly in quadratic time, and which can perform function composition for any fixed number of functions. Prior mechanisms, even for just composing two functions, could only be computed in superquadratic time, and our new lower bounds show that faster algorithms for them are not possible.

---

### SafeGround: Know When to Trust GUI Grounding Models via Uncertainty Calibration

Authors: Qingni Wang, Yue Fan, Xin Eric Wang
Published: 2026-02-02
Categories: cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2602.02419v2

Graphical User Interface (GUI) grounding aims to translate natural language instructions into executable screen coordinates, enabling automated GUI interaction. Nevertheless, incorrect grounding can result in costly, hard-to-reverse actions (e.g., erroneous payment approvals), raising concerns about model reliability. In this paper, we introduce SafeGround, an uncertainty-aware framework for GUI grounding models that enables risk-aware predictions through calibrations before testing. SafeGround leverages a distribution-aware uncertainty quantification method to capture the spatial dispersion of stochastic samples from outputs of any given model. Then, through the calibration process, SafeGround derives a test-time decision threshold with statistically guaranteed false discovery rate (FDR) control. We apply SafeGround on multiple GUI grounding models for the challenging ScreenSpot-Pro benchmark. Experimental results show that our uncertainty measure consistently outperforms existing baselines in distinguishing correct from incorrect predictions, while the calibrated threshold reliably enables rigorous risk control and potentials of substantial system-level accuracy improvements. Across multiple GUI grounding models, SafeGround improves system-level accuracy by up to 5.38% percentage points over Gemini-only inference.

---

### Trust Region Continual Learning as an Implicit Meta-Learner

Authors: Zekun Wang, Anant Gupta, Christopher J. MacLellan
Published: 2026-02-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.02417v2

Continual learning aims to acquire tasks sequentially without catastrophic forgetting, yet standard strategies face a core tradeoff: regularization-based methods (e.g., EWC) can overconstrain updates when task optima are weakly overlapping, while replay-based methods can retain performance but drift due to imperfect replay. We study a hybrid perspective: \emph{trust region continual learning} that combines generative replay with a Fisher-metric trust region constraint. We show that, under local approximations, the resulting update admits a MAML-style interpretation with a single implicit inner step: replay supplies an old-task gradient signal (query-like), while the Fisher-weighted penalty provides an efficient offline curvature shaping (support-like). This yields an emergent meta-learning property in continual learning: the model becomes an initialization that rapidly \emph{re-converges} to prior task optima after each task transition, without explicitly optimizing a bilevel objective. Empirically, on task-incremental diffusion image generation and continual diffusion-policy control, trust region continual learning achieves the best final performance and retention, and consistently recovers early-task performance faster than EWC, replay, and continual meta-learning baselines.

---

### Structure Enables Effective Self-Localization of Errors in LLMs

Authors: Ankur Samanta, Akshayaa Magesh, Ayush Jain, Kavosh Asadi, Youliang Yu, Daniel Jiang, Boris Vidolov, Kaveh Hassani, Paul Sajda, Jalaj Bhandari, Yonathan Efroni
Published: 2026-02-02
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.02416v2

Self-correction in language models remains elusive. In this work, we explore whether language models can explicitly localize errors in incorrect reasoning, as a path toward building AI systems that can effectively correct themselves. We introduce a prompting method that structures reasoning as discrete, semantically coherent thought steps, and show that models can localize errors more reliably within this structure than in conventional, unstructured chain-of-thought reasoning. Motivated by how the human brain monitors errors at discrete decision points and resamples alternatives, we introduce Iterative Correction Sampling of Thoughts (Thought-ICS), a self-correction framework. Thought-ICS iteratively prompts the model to generate reasoning one discrete and complete thought at a time--where each thought represents a deliberate decision by the model--creating natural boundaries for precise error localization. Upon verification, the model localizes the first erroneous step, and the system backtracks to generate alternative reasoning from the last correct point. When asked to correct reasoning verified as incorrect by an oracle, Thought-ICS achieves 20-40% self-correction lift. In a completely autonomous setting without external verification, it outperforms contemporary self-correction baselines.

---

### Active Transfer Bagging: A New Approach for Accelerated Active Learning Acquisition of Data by Combined Transfer Learning and Bagging Based Models

Authors: Vivienne Pelletier, Daniel J. Rivera, Obinna Nwokonkwo, Steven A. Wilson, Christopher L. Muhich
Published: 2026-02-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.02415v1

Modern machine learning has achieved remarkable success on many problems, but this success often depends on the existence of large, labeled datasets. While active learning can dramatically reduce labeling cost when annotations are expensive, early performance is frequently dominated by the initial seed set, typically chosen at random. In many applications, however, related or approximate datasets are readily available and can be leveraged to construct a better seed set. We introduce a new method for selecting the seed data set for active learning, Active-Transfer Bagging (ATBagging). ATBagging estimates the informativeness of candidate data point from a Bayesian interpretation of bagged ensemble models by comparing in-bag and out-of-bag predictive distributions from the labeled dataset, yielding an information-gain proxy. To avoid redundant selections, we impose feature-space diversity by sampling a determinantal point process (DPP) whose kernel uses Random Fourier Features and a quality-diversity factorization that incorporates the informativeness scores. This same blended method is used for selection of new data points to collect during the active learning phase. We evaluate ATBagging on four real-world datasets covering both target-transfer and feature-shift scenarios (QM9, ERA5, Forbes 2000, and Beijing PM2.5). Across seed sizes nseed = 10-100, ATBagging improves or ties early active learning and increases area under the learning-curve relative to alternative seed subset selection methodologies in almost all cases, with strongest benefits in low-data regimes. Thus, ATBagging provides a low-cost, high reward means to initiating active learning-based data collection.

---

### Misconception Diagnosis From Student-Tutor Dialogue: Generate, Retrieve, Rerank

Authors: Joshua Mitton, Prarthana Bhattacharyya, Digory Smith, Thomas Christie, Ralph Abboud, Simon Woodhead
Published: 2026-02-02
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.02414v2

Timely and accurate identification of student misconceptions is key to improving learning outcomes and pre-empting the compounding of student errors. However, this task is highly dependent on the effort and intuition of the teacher. In this work, we present a novel approach for detecting misconceptions from student-tutor dialogues using large language models (LLMs). First, we use a fine-tuned LLM to generate plausible misconceptions, and then retrieve the most promising candidates among these using embedding similarity with the input dialogue. These candidates are then assessed and re-ranked by another fine-tuned LLM to improve misconception relevance. Empirically, we evaluate our system on real dialogues from an educational tutoring platform. We consider multiple base LLM models including LLaMA, Qwen and Claude on zero-shot and fine-tuned settings. We find that our approach improves predictive performance over baseline models and that fine-tuning improves both generated misconception quality and can outperform larger closed-source models. Finally, we conduct ablation studies to both validate the importance of our generation and reranking steps on misconception generation quality.

---

### Misconception Diagnosis From Student-Tutor Dialogue: Generate, Retrieve, Rerank

Authors: Joshua Mitton, Prarthana Bhattacharyya, Digory Smith, Thomas Christie, Ralph Abboud, Simon Woodhead
Published: 2026-02-02
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.02414v1

Timely and accurate identification of student misconceptions is key to improving learning outcomes and pre-empting the compounding of student errors. However, this task is highly dependent on the effort and intuition of the teacher. In this work, we present a novel approach for detecting misconceptions from student-tutor dialogues using large language models (LLMs). First, we use a fine-tuned LLM to generate plausible misconceptions, and then retrieve the most promising candidates among these using embedding similarity with the input dialogue. These candidates are then assessed and re-ranked by another fine-tuned LLM to improve misconception relevance. Empirically, we evaluate our system on real dialogues from an educational tutoring platform. We consider multiple base LLM models including LLaMA, Qwen and Claude on zero-shot and fine-tuned settings. We find that our approach improves predictive performance over baseline models and that fine-tuning improves both generated misconception quality and can outperform larger closed-source models. Finally, we conduct ablation studies to both validate the importance of our generation and reranking steps on misconception generation quality.

---

### Masked Autoencoders as Universal Speech Enhancer

Authors: Rajalaxmi Rajagopalan, Ritwik Giri, Zhiqiang Tang, Kyu Han
Published: 2026-02-02
Categories: cs.SD, cs.LG
arXiv: https://arxiv.org/abs/2602.02413v1

Supervised speech enhancement methods have been very successful. However, in practical scenarios, there is a lack of clean speech, and self-supervised learning-based (SSL) speech enhancement methods that offer comparable enhancement performance and can be applied to other speech-related downstream applications are desired. In this work, we develop a masked autoencoder based universal speech enhancer that is agnostic to the type of distortion affecting speech, can handle multiple distortions simultaneously, and is trained in a self-supervised manner. An augmentation stack adds further distortions to the noisy input data. The masked autoencoder model learns to remove the added distortions along with reconstructing the masked regions of the spectrogram during pre-training. The pre-trained embeddings are then used by fine-tuning models trained on a small amount of paired data for specific downstream tasks. We evaluate the pre-trained features for denoising and dereverberation downstream tasks. We explore different augmentations (like single or multi-speaker) in the pre-training augmentation stack and the effect of different noisy input feature representations (like $log1p$ compression) on pre-trained embeddings and downstream fine-tuning enhancement performance. We show that the proposed method not only outperforms the baseline but also achieves state-of-the-art performance for both in-domain and out-of-domain evaluation datasets.

---

### Catalyst: Out-of-Distribution Detection via Elastic Scaling

Authors: Abid Hassan, Tuan Ngo, Saad Shafiq, Nenad Medvidovic
Published: 2026-02-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.02409v3

Out-of-distribution (OOD) detection is critical for the safe deployment of deep neural networks. State-of-the-art post-hoc methods typically derive OOD scores from the output logits or penultimate feature vector obtained via global average pooling (GAP). We contend that this exclusive reliance on the logit or feature vector discards a rich, complementary signal: the raw channel-wise statistics of the pre-pooling feature map lost in GAP. In this paper, we introduce Catalyst, a post-hoc framework that exploits these under-explored signals. Catalyst computes an input-dependent scaling factor ($γ$) on-the-fly from these raw statistics (e.g., mean, standard deviation, and maximum activation). This $γ$ is then fused with the existing baseline score, multiplicatively modulating it -- an $\textit{elastic scaling}$ -- to push the ID and OOD distributions further apart. We demonstrate Catalyst is a generalizable framework: it seamlessly integrates with logit-based methods (e.g., Energy, ReAct, SCALE) and also provides a significant boost to distance-based detectors like KNN. As a result, Catalyst achieves substantial and consistent performance gains, reducing the average False Positive Rate by 32.87 on CIFAR-10 (ResNet-18), 27.94% on CIFAR-100 (ResNet-18), and 22.25% on ImageNet (ResNet-50). Our results highlight the untapped potential of pre-pooling statistics and demonstrate that Catalyst is complementary to existing OOD detection approaches. Our code is available here: https://github.com/bingabid/Catalyst

---

### ReasonEdit: Editing Vision-Language Models using Human Reasoning

Authors: Jiaxing Qiu, Kaihua Hou, Roxana Daneshjou, Ahmed Alaa, Thomas Hartvigsen
Published: 2026-02-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.02408v5

Model editing aims to correct errors in large, pretrained models without altering unrelated behaviors. While some recent works have edited vision-language models (VLMs), no existing editors tackle reasoning-heavy tasks, which typically require humans and models to reason about images. We therefore propose ReasonEdit, the first VLM editor to let users explain their reasoning during editing, introducing a new, practical model editing setup. ReasonEdit continuously stores human reasoning in a codebook, and retrieves only relevant facts during inference using a novel topology-balanced multimodal embedding method inspired by network science. Across four VLMs on multiple rationale-based visual question answering datasets, ReasonEdit achieves state-of-the-art editing performance, ultimately showing that using human reasoning during editing greatly improves edit generalization.

---

### ReasonEdit: Editing Vision-Language Models using Human Reasoning

Authors: Jiaxing Qiu, Kaihua Hou, Roxana Daneshjou, Ahmed Alaa, Thomas Hartvigsen
Published: 2026-02-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.02408v4

Model editing aims to correct errors in large, pretrained models without altering unrelated behaviors. While some recent works have edited vision-language models (VLMs), no existing editors tackle reasoning-heavy tasks, which typically require humans and models to reason about images. We therefore propose ReasonEdit, the first VLM editor to let users explain their reasoning during editing, introducing a new, practical model editing setup. ReasonEdit continuously stores human reasoning in a codebook, and retrieves only relevant facts during inference using a novel topology-balanced multimodal embedding method inspired by network science. Across four VLMs on multiple rationale-based visual question answering datasets, ReasonEdit achieves state-of-the-art editing performance, ultimately showing that using human reasoning during editing greatly improves edit generalization.

---

### Provably Data-driven Multiple Hyper-parameter Tuning with Structured Loss Function

Authors: Tung Quoc Le, Anh Tuan Nguyen, Viet Anh Nguyen
Published: 2026-02-02
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.02406v2

Data-driven algorithm design automates hyperparameter tuning, but its statistical foundations remain limited because model performance can depend on hyperparameters in implicit and highly non-smooth ways. Existing guarantees focus on the simple case of a one-dimensional (scalar) hyperparameter. This leaves the practically important, multi-dimensional hyperparameter tuning setting unresolved. We address this open question by establishing the first general framework for establishing generalization guarantees for tuning multi-dimensional hyperparameters in data-driven settings. Our approach strengthens the generalization guarantee framework for semi-algebraic function classes by exploiting tools from real algebraic geometry, yielding sharper, more broadly applicable guarantees. For completeness, we also instantiate the first lower bound for this general setting. We further extend the analysis to hyperparameter tuning using the validation loss under minimal assumptions, and derive improved bounds when additional structure is available. Finally, we demonstrate the scope of the framework with new learnability results, including data-driven weighted group lasso and weighted fused lasso.

---

### Making Expert Reasoning Learnable with Self-Distillation

Authors: Ethan Mendes, Jungsoo Park, Alan Ritter
Published: 2026-02-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.02405v2

Improving the reasoning capabilities of large language models (LLMs) typically relies either on the model's ability to sample a correct solution to be reinforced or the existence of a stronger model able to solve the problem. However, many difficult problems remain intractable for even current frontier models, preventing the extraction of valid training signals. A promising alternative is to leverage high-quality expert human solutions, yet naive imitation of this data fails because it is fundamentally out-of-distribution: expert solutions are typically didactic, containing implicit reasoning gaps intended for human readers rather than computational models. Furthermore, high-quality expert solutions are expensive, necessitating generalizable, sample-efficient training methods. We propose Distribution Aligned Imitation Learning (DAIL), a two-step self-distillation method that bridges the distributional gap by first transforming expert solutions into detailed, in-distribution reasoning traces and then applying a contrastive objective to focus learning on expert insights and methodologies. We find that DAIL can leverage fewer than 1000 high-quality expert solutions to achieve up to 31% pass@128 gains on Qwen2.5-Instruct and Qwen3, double reasoning efficiency, and enable out-of-domain generalization.

---

### SoMA: A Real-to-Sim Neural Simulator for Robotic Soft-body Manipulation

Authors: Mu Huang, Hui Wang, Kerui Ren, Linning Xu, Yunsong Zhou, Mulin Yu, Bo Dai, Jiangmiao Pang
Published: 2026-02-02
Categories: cs.RO, cs.AI, cs.CV, physics.app-ph
arXiv: https://arxiv.org/abs/2602.02402v2

Simulating deformable objects under rich interactions remains a fundamental challenge for real-to-sim robot manipulation, with dynamics jointly driven by environmental effects and robot actions. Existing simulators rely on predefined physics or data-driven dynamics without robot-conditioned control, limiting accuracy, stability, and generalization. This paper presents SoMA, a 3D Gaussian Splat simulator for soft-body manipulation. SoMA couples deformable dynamics, environmental forces, and robot joint actions in a unified latent neural space for end-to-end real-to-sim simulation. Modeling interactions over learned Gaussian splats enables controllable, stable long-horizon manipulation and generalization beyond observed trajectories without predefined physical models. SoMA improves resimulation accuracy and generalization on real-world robot manipulation by 20%, enabling stable simulation of complex tasks such as long-horizon cloth folding.

---

### Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation

Authors: Xinshun Wang, Peiming Li, Ziyi Wang, Zhongbin Fang, Zhichao Deng, Songtao Wu, Jason Li, Mengyuan Liu
Published: 2026-02-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.02401v2

Human motion analysis tasks, such as temporal 3D pose estimation, motion prediction, and motion in-betweening, play an essential role in computer vision. However, current paradigms suffer from severe fragmentation. First, the field is split between ``perception'' models that understand motion from video but only output text, and ``generation'' models that cannot perceive from raw visual input. Second, generative MLLMs are often limited to single-frame, static poses using dense, parametric SMPL models, failing to handle temporal motion. Third, existing motion vocabularies are built from skeleton data alone, severing the link to the visual domain. To address these challenges, we introduce Superman, a unified framework that bridges visual perception with temporal, skeleton-based motion generation. Our solution is twofold. First, to overcome the modality disconnect, we propose a Vision-Guided Motion Tokenizer. Leveraging the natural geometric alignment between 3D skeletons and visual data, this module pioneers robust joint learning from both modalities, creating a unified, cross-modal motion vocabulary. Second, grounded in this motion language, a single, unified MLLM architecture is trained to handle all tasks. This module flexibly processes diverse, temporal inputs, unifying 3D skeleton pose estimation from video (perception) with skeleton-based motion prediction and in-betweening (generation). Extensive experiments on standard benchmarks, including Human3.6M, demonstrate that our unified method achieves state-of-the-art or competitive performance across all motion tasks. This showcases a more efficient and scalable path for generative motion analysis using skeletons.

---

### An Empirical Study on Noisy Data and LLM Pretraining Loss Divergence

Authors: Qizhen Zhang, Ankush Garg, Jakob Foerster, Niladri Chatterji, Kshitiz Malik, Mike Lewis
Published: 2026-02-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.02400v1

Large-scale pretraining datasets drive the success of large language models (LLMs). However, these web-scale corpora inevitably contain large amounts of noisy data due to unregulated web content or randomness inherent in data. Although LLM pretrainers often speculate that such noise contributes to instabilities in large-scale LLM pretraining and, in the worst cases, loss divergence, this phenomenon remains poorly understood.In this work, we present a systematic empirical study of whether noisy data causes LLM pretraining divergences and how it does so. By injecting controlled synthetic uniformly random noise into otherwise clean datasets, we analyze training dynamics across model sizes ranging from 480M to 5.2B parameters. We show that noisy data indeed induces training loss divergence, and that the probability of divergence depends strongly on the noise type, amount of noise, and model scale. We further find that noise-induced divergences exhibit activation patterns distinct from those caused by high learning rates, and we provide diagnostics that differentiate these two failure modes. Together, these results provide a large-scale, controlled characterization of how noisy data affects loss divergence in LLM pretraining.

---

### PRISM: Performer RS-IMLE for Single-pass Multisensory Imitation Learning

Authors: Amisha Bhaskar, Pratap Tokekar, Stefano Di Cairano, Alexander Schperberg
Published: 2026-02-02
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2602.02396v1

Robotic imitation learning typically requires models that capture multimodal action distributions while operating at real-time control rates and accommodating multiple sensing modalities. Although recent generative approaches such as diffusion models, flow matching, and Implicit Maximum Likelihood Estimation (IMLE) have achieved promising results, they often satisfy only a subset of these requirements. To address this, we introduce PRISM, a single-pass policy based on a batch-global rejection-sampling variant of IMLE. PRISM couples a temporal multisensory encoder (integrating RGB, depth, tactile, audio, and proprioception) with a linear-attention generator using a Performer architecture. We demonstrate the efficacy of PRISM on a diverse real-world hardware suite, including loco-manipulation using a Unitree Go2 with a 7-DoF arm D1 and tabletop manipulation with a UR5 manipulator. Across challenging physical tasks such as pre-manipulation parking, high-precision insertion, and multi-object pick-and-place, PRISM outperforms state-of-the-art diffusion policies by 10-25% in success rate while maintaining high-frequency (30-50 Hz) closed-loop control. We further validate our approach on large-scale simulation benchmarks, including CALVIN, MetaWorld, and Robomimic. In CALVIN (10% data split), PRISM improves success rates by approximately 25% over diffusion and approximately 20% over flow matching, while simultaneously reducing trajectory jerk by 20x-50x. These results position PRISM as a fast, accurate, and multisensory imitation policy that retains multimodal action coverage without the latency of iterative sampling.

---

### David vs. Goliath: Verifiable Agent-to-Agent Jailbreaking via Reinforcement Learning

Authors: Samuel Nellessen, Tal Kachman
Published: 2026-02-02
Categories: cs.LG, cs.AI, cs.CR, cs.MA
arXiv: https://arxiv.org/abs/2602.02395v1

The evolution of large language models into autonomous agents introduces adversarial failures that exploit legitimate tool privileges, transforming safety evaluation in tool-augmented environments from a subjective NLP task into an objective control problem. We formalize this threat model as Tag-Along Attacks: a scenario where a tool-less adversary "tags along" on the trusted privileges of a safety-aligned Operator to induce prohibited tool use through conversation alone. To validate this threat, we present Slingshot, a 'cold-start' reinforcement learning framework that autonomously discovers emergent attack vectors, revealing a critical insight: in our setting, learned attacks tend to converge to short, instruction-like syntactic patterns rather than multi-turn persuasion. On held-out extreme-difficulty tasks, Slingshot achieves a 67.0% success rate against a Qwen2.5-32B-Instruct-AWQ Operator (vs. 1.7% baseline), reducing the expected attempts to first success (on solved tasks) from 52.3 to 1.3. Crucially, Slingshot transfers zero-shot to several model families, including closed-source models like Gemini 2.5 Flash (56.0% attack success rate) and defensive-fine-tuned open-source models like Meta-SecAlign-8B (39.2% attack success rate). Our work establishes Tag-Along Attacks as a first-class, verifiable threat model and shows that effective agentic attacks can be elicited from off-the-shelf open-weight models through environment interaction alone.

---

### Infinite-World: Scaling Interactive World Models to 1000-Frame Horizons via Pose-Free Hierarchical Memory

Authors: Ruiqi Wu, Xuanhua He, Meng Cheng, Tianyu Yang, Yong Zhang, Zhuoliang Kang, Xunliang Cai, Xiaoming Wei, Chunle Guo, Chongyi Li, Ming-Ming Cheng
Published: 2026-02-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.02393v2

We propose Infinite-World, a robust interactive world model capable of maintaining coherent visual memory over 1000+ frames in complex real-world environments. While existing world models can be efficiently optimized on synthetic data with perfect ground-truth, they lack an effective training paradigm for real-world videos due to noisy pose estimations and the scarcity of viewpoint revisits. To bridge this gap, we first introduce a Hierarchical Pose-free Memory Compressor (HPMC) that recursively distills historical latents into a fixed-budget representation. By jointly optimizing the compressor with the generative backbone, HPMC enables the model to autonomously anchor generations in the distant past with bounded computational cost, eliminating the need for explicit geometric priors. Second, we propose an Uncertainty-aware Action Labeling module that discretizes continuous motion into a tri-state logic. This strategy maximizes the utilization of raw video data while shielding the deterministic action space from being corrupted by noisy trajectories, ensuring robust action-response learning. Furthermore, guided by insights from a pilot toy study, we employ a Revisit-Dense Finetuning Strategy using a compact, 30-minute dataset to efficiently activate the model's long-range loop-closure capabilities. Extensive experiments, including objective metrics and user studies, demonstrate that Infinite-World achieves superior performance in visual quality, action controllability, and spatial consistency.

---

### Personalized Image Generation via Human-in-the-loop Bayesian Optimization

Authors: Rajalaxmi Rajagopalan, Debottam Dutta, Yu-Lin Wei, Romit Roy Choudhury
Published: 2026-02-02
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.02388v2

Imagine Alice has a specific image $x^\ast$ in her mind, say, the view of the street in which she grew up during her childhood. To generate that exact image, she guides a generative model with multiple rounds of prompting and arrives at an image $x^{p*}$. Although $x^{p*}$ is reasonably close to $x^\ast$, Alice finds it difficult to close that gap using language prompts. This paper aims to narrow this gap by observing that even after language has reached its limits, humans can still tell when a new image $x^+$ is closer to $x^\ast$ than $x^{p*}$. Leveraging this observation, we develop MultiBO (Multi-Choice Preferential Bayesian Optimization) that carefully generates $K$ new images as a function of $x^{p*}$, gets preferential feedback from the user, uses the feedback to guide the diffusion model, and ultimately generates a new set of $K$ images. We show that within $B$ rounds of user feedback, it is possible to arrive much closer to $x^\ast$, even though the generative model has no information about $x^\ast$. Qualitative scores from $30$ users, combined with quantitative metrics compared across $5$ baselines, show promising results, suggesting that multi-choice feedback from humans can be effectively harnessed for personalized image generation.

---

### Trust by Design: Skill Profiles for Transparent, Cost-Aware LLM Routing

Authors: Mika Okamoto, Ansel Kaplan Erol, Glenn Matlin
Published: 2026-02-02
Categories: cs.AI, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2602.02386v1

How should Large Language Model (LLM) practitioners select the right model for a task without wasting money? We introduce BELLA (Budget-Efficient LLM Selection via Automated skill-profiling), a framework that recommends optimal LLM selection for tasks through interpretable skill-based model selection. Standard benchmarks report aggregate metrics that obscure which specific capabilities a task requires and whether a cheaper model could suffice. BELLA addresses this gap through three stages: (1) decomposing LLM outputs and extract the granular skills required by using critic-based profiling, (2) clustering skills into structured capability matrices, and (3) multi-objective optimization to select the right models to maximize performance while respecting budget constraints. BELLA provides natural-language rationale for recommendations, providing transparency that current black-box routing systems lack. We describe the framework architecture, situate it within the landscape of LLM routing and evaluation, and discuss its application to financial reasoning as a representative domain exhibiting diverse skill requirements and cost-variation across models. Our framework enables practitioners to make principled and cost-performance trade-offs for deploying LLMs.

---

### Transformers learn factored representations

Authors: Adam Shai, Loren Amdahl-Culleton, Casper L. Christensen, Henry R. Bigelow, Fernando E. Rosas, Alexander B. Boyd, Eric A. Alt, Kyle J. Ray, Paul M. Riechers
Published: 2026-02-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.02385v1

Transformers pretrained via next token prediction learn to factor their world into parts, representing these factors in orthogonal subspaces of the residual stream. We formalize two representational hypotheses: (1) a representation in the product space of all factors, whose dimension grows exponentially with the number of parts, or (2) a factored representation in orthogonal subspaces, whose dimension grows linearly. The factored representation is lossless when factors are conditionally independent, but sacrifices predictive fidelity otherwise, creating a tradeoff between dimensional efficiency and accuracy. We derive precise predictions about the geometric structure of activations for each, including the number of subspaces, their dimensionality, and the arrangement of context embeddings within them. We test between these hypotheses on transformers trained on synthetic processes with known latent structure. Models learn factored representations when factors are conditionally independent, and continue to favor them early in training even when noise or hidden dependencies undermine conditional independence, reflecting an inductive bias toward factoring at the cost of fidelity. This provides a principled explanation for why transformers decompose the world into parts, and suggests that interpretable low dimensional structure may persist even in models trained on complex data.

---

### SLIME: Stabilized Likelihood Implicit Margin Enforcement for Preference Optimization

Authors: Maksim Afanasyev, Illarion Iov
Published: 2026-02-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.02383v2

Direct preference optimization methods have emerged as a computationally efficient alternative to Reinforcement Learning from Human Feedback (RLHF) for aligning Large Language Models (LLMs). Latest approaches have streamlined the alignment process by deriving implicit reward functions, yet they often suffer from a critical objective mismatch: optimizing the relative margin between chosen and rejected responses does not guarantee the preservation of the chosen response's absolute likelihood. This can lead to unlearning, where the model degrades the probability of high-quality outputs to satisfy margin constraints, and formatting collapse caused by the over-penalization of rejected sequences. In this work, we introduce SLIME (Stabilized Likelihood Implicit Margin Enforcement), a reference-free alignment objective designed to decouple preference learning from generation quality. SLIME incorporates a three-pronged objective: (1) an anchoring term to maximize the likelihood of preferred responses; (2) a stabilizing penalty that prevents the probabilities of rejected tokens from collapsing to zero; and (3) a dual-margin mechanism that combines hard and soft constraints for precise boundary shaping. Our results demonstrate that SLIME achieves superior performance compared to state-of-the-art baselines while maintaining higher generation stability.

---

### ROG: Retrieval-Augmented LLM Reasoning for Complex First-Order Queries over Knowledge Graphs

Authors: Ziyan Zhang, Chao Wang, Zhuo Chen, Chiyi Li, Kai Song
Published: 2026-02-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.02382v1

Answering first-order logic (FOL) queries over incomplete knowledge graphs (KGs) is difficult, especially for complex query structures that compose projection, intersection, union, and negation. We propose ROG, a retrieval-augmented framework that combines query-aware neighborhood retrieval with large language model (LLM) chain-of-thought reasoning. ROG decomposes a multi-operator query into a sequence of single-operator sub-queries and grounds each step in compact, query-relevant neighborhood evidence. Intermediate answer sets are cached and reused across steps, improving consistency on deep reasoning chains. This design reduces compounding errors and yields more robust inference on complex and negation-heavy queries. Overall, ROG provides a practical alternative to embedding-based logical reasoning by replacing learned operators with retrieval-grounded, step-wise inference. Experiments on standard KG reasoning benchmarks show consistent gains over strong embedding-based baselines, with the largest improvements on high-complexity and negation-heavy query types.

---

### Self-Supervised Learning from Structural Invariance

Authors: Yipeng Zhang, Hafez Ghaemi, Jungyoon Lee, Shahab Bakhtiari, Eilif B. Muller, Laurent Charlin
Published: 2026-02-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.02381v2

Joint-embedding self-supervised learning (SSL), the key paradigm for unsupervised representation learning from visual data, learns from invariances between semantically-related data pairs. We study the one-to-many mapping problem in SSL, where each datum may be mapped to multiple valid targets. This arises when data pairs come from naturally occurring generative processes, e.g., successive video frames. We show that existing methods struggle to flexibly capture this conditional uncertainty. As a remedy, we introduce a latent variable to account for this uncertainty and derive a variational lower bound on the mutual information between paired embeddings. Our derivation yields a simple regularization term for standard SSL objectives. The resulting method, which we call AdaSSL, applies to both contrastive and distillation-based SSL objectives, and we empirically show its versatility in causal representation learning, fine-grained image understanding, and world modeling on videos.

---

### Unified Personalized Reward Model for Vision Generation

Authors: Yibin Wang, Yuhang Zang, Feng Han, Jiazi Bu, Yujie Zhou, Cheng Jin, Jiaqi Wang
Published: 2026-02-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.02380v2

Recent advancements in multimodal reward models (RMs) have significantly propelled the development of visual generation. Existing frameworks typically adopt Bradley-Terry-style preference modeling or leverage generative VLMs as judges, and subsequently optimize visual generation models via reinforcement learning. However, current RMs suffer from inherent limitations: they often follow a one-size-fits-all paradigm that assumes a monolithic preference distribution or relies on fixed evaluation rubrics. As a result, they are insensitive to content-specific visual cues, leading to systematic misalignment with subjective and context-dependent human preferences. To this end, inspired by human assessment, we propose UnifiedReward-Flex, a unified personalized reward model for vision generation that couples reward modeling with flexible and context-adaptive reasoning. Specifically, given a prompt and the generated visual content, it first interprets the semantic intent and grounds on visual evidence, then dynamically constructs a hierarchical assessment by instantiating fine-grained criteria under both predefined and self-generated high-level dimensions. Our training pipeline follows a two-stage process: (1) we first distill structured, high-quality reasoning traces from advanced closed-source VLMs to bootstrap SFT, equipping the model with flexible and context-adaptive reasoning behaviors; (2) we then perform direct preference optimization (DPO) on carefully curated preference pairs to further strengthen reasoning fidelity and discriminative alignment. To validate the effectiveness, we integrate UnifiedReward-Flex into the GRPO framework for image and video synthesis, and extensive results demonstrate its superiority.

---

### From Sycophancy to Sensemaking: Premise Governance for Human-AI Decision Making

Authors: Raunak Jain
Published: 2026-02-02
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.02378v2

As LLMs expand from assistance to decision support, a dangerous pattern emerges: fluent agreement without calibrated judgment. Low-friction assistants can become sycophantic, baking in implicit assumptions and pushing verification costs onto experts, while outcomes arrive too late to serve as reward signals. In deep-uncertainty decisions (where objectives are contested and reversals are costly), scaling fluent agreement amplifies poor commitments faster than it builds expertise. We argue reliable human-AI partnership requires a shift from answer generation to collaborative premise governance over a knowledge substrate, negotiating only what is decision-critical. A discrepancy-driven control loop operates over this substrate: detecting conflicts, localizing misalignment via typed discrepancies (teleological, epistemic, procedural), and triggering bounded negotiation through decision slices. Commitment gating blocks action on uncommitted load-bearing premises unless overridden under logged risk; value-gated challenge allocates probing under interaction cost. Trust then attaches to auditable premises and evidence standards, not conversational fluency. We illustrate with tutoring and propose falsifiable evaluation criteria.

---

### ProofVerifier: A Scalable, Diversity-Driven Framework for Natural-Language Proof Verification

Authors: Haotong Yang, Zitong Wang, Shijia Kang, Siqi Yang, Wenkai Yu, Xu Niu, Yike Sun, Yi Hu, Zhouchen Lin, Muhan Zhang
Published: 2026-02-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.02377v3

While large language models (LLMs) have achieved strong performance on mathematical problems with verifiable answers, many advanced problems are proof-based and require evaluating full proofs. However, training such verifiers requires diverse and trustworthy question-proof-check (QPC) examples at scale, which are scarce. To address this challenge, we develop a human-audited, LLM-assisted data pipeline that produces large-scale QPC triplets with limited human effort. By systematically varying problem sources, generation strategies, and generator models, the pipeline creates diverse problem-proof pairs spanning multiple difficulty levels, linguistic styles, and error types. We combine multi-LLM agreement with hierarchical human auditing to obtain accurate proof-correctness labels. Using these data, we train generative proof verifiers and introduce an auxiliary fluency filter together with balanced token weighting to stabilize binary-reward long-form verification RL. Experiments show that our verifier improves proof-judgment accuracy across different proof styles and provides useful guidance for test-time selection. Overall, our results provide a practical data and training framework for natural-language proof verification.

---

### Proof-RM: A Scalable and Generalizable Reward Model for Math Proof

Authors: Haotong Yang, Zitong Wang, Shijia Kang, Siqi Yang, Wenkai Yu, Xu Niu, Yike Sun, Yi Hu, Zhouchen Lin, Muhan Zhang
Published: 2026-02-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.02377v2

While Large Language Models (LLMs) have demonstrated strong math reasoning abilities through Reinforcement Learning with *Verifiable Rewards* (RLVR), many advanced mathematical problems are proof-based, with no guaranteed way to determine the authenticity of a proof by simple answer matching. To enable automatic verification, a Reward Model (RM) capable of reliably evaluating full proof processes is required. In this work, we design a *scalable* data-construction pipeline that, with minimal human effort, leverages LLMs to generate a large quantity of high-quality ``**question-proof-check**'' triplet data. By systematically varying problem sources, generation methods, and model configurations, we create diverse problem-proof pairs spanning multiple difficulty levels, linguistic styles, and error types, subsequently filtered through hierarchical human review for label alignment. Utilizing these data, we train a proof-checking RM, incorporating an ``LLM-as-a-RM-for-RM'' approach and balanced token weighting to stabilize the RL process. Our experiments validate the model's scalability and strong performance from multiple perspectives, including reward accuracy, generalization ability and test-time guidance, providing important practical recipes and tools for strengthening LLM mathematical capabilities.

---

### C-kNN-LSH: A Nearest-Neighbor Algorithm for Sequential Counterfactual Inference

Authors: Jing Wang, Jie Shen, Qiaomin Xie, Jeremy C Weiss
Published: 2026-02-02
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2602.02371v1

Estimating causal effects from longitudinal trajectories is central to understanding the progression of complex conditions and optimizing clinical decision-making, such as comorbidities and long COVID recovery. We introduce \emph{C-kNN--LSH}, a nearest-neighbor framework for sequential causal inference designed to handle such high-dimensional, confounded situations. By utilizing locality-sensitive hashing, we efficiently identify ``clinical twins'' with similar covariate histories, enabling local estimation of conditional treatment effects across evolving disease states. To mitigate bias from irregular sampling and shifting patient recovery profiles, we integrate neighborhood estimator with a doubly-robust correction. Theoretical analysis guarantees our estimator is consistent and second-order robust to nuisance error. Evaluated on a real-world Long COVID cohort with 13,511 participants, \emph{C-kNN-LSH} demonstrates superior performance in capturing recovery heterogeneity and estimating policy values compared to existing baselines.

---

### Uncertainty-Aware Image Classification In Biomedical Imaging Using Spectral-normalized Neural Gaussian Processes

Authors: Uma Meleti, Jeffrey J. Nirschl
Published: 2026-02-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.02370v2

Accurate histopathologic interpretation is key for clinical decision-making; however, current deep learning models for digital pathology are often overconfident and poorly calibrated in out-of-distribution (OOD) settings, which limit trust and clinical adoption. Safety-critical medical imaging workflows benefit from intrinsic uncertainty-aware properties that can accurately reject OOD input. We implement the Spectral-normalized Neural Gaussian Process (SNGP), a set of lightweight modifications that apply spectral normalization and replace the final dense layer with a Gaussian process layer to improve single-model uncertainty estimation and OOD detection. We evaluate SNGP vs. deterministic and MonteCarlo dropout on six datasets across three biomedical classification tasks: white blood cells, amyloid plaques, and colorectal histopathology. SNGP has comparable in-distribution performance while significantly improving uncertainty estimation and OOD detection. Thus, SNGP or related models offer a useful framework for uncertainty-aware classification in digital pathology, supporting safe deployment and building trust with pathologists.

---

### Live-Evo: Online Evolution of Agentic Memory from Continuous Feedback

Authors: Yaolun Zhang, Yiran Wu, Yijiong Yu, Qingyun Wu, Huazheng Wang
Published: 2026-02-02
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.02369v1

Large language model (LLM) agents are increasingly equipped with memory, which are stored experience and reusable guidance that can improve task-solving performance. Recent \emph{self-evolving} systems update memory based on interaction outcomes, but most existing evolution pipelines are developed for static train/test splits and only approximate online learning by folding static benchmarks, making them brittle under true distribution shift and continuous feedback. We introduce \textsc{Live-Evo}, an online self-evolving memory system that learns from a stream of incoming data over time. \textsc{Live-Evo} decouples \emph{what happened} from \emph{how to use it} via an Experience Bank and a Meta-Guideline Bank, compiling task-adaptive guidelines from retrieved experiences for each task. To manage memory online, \textsc{Live-Evo} maintains experience weights and updates them from feedback: experiences that consistently help are reinforced and retrieved more often, while misleading or stale experiences are down-weighted and gradually forgotten, analogous to reinforcement and decay in human memory. On the live \textit{Prophet Arena} benchmark over a 10-week horizon, \textsc{Live-Evo} improves Brier score by 20.8\% and increases market returns by 12.9\%, while also transferring to deep-research benchmarks with consistent gains over strong baselines. Our code is available at https://github.com/ag2ai/Live-Evo.

---

### ReasonCACHE: Teaching LLMs To Reason Without Weight Updates

Authors: Sharut Gupta, Phillip Isola, Stefanie Jegelka, David Lopez-Paz, Kartik Ahuja, Mark Ibrahim, Mohammad Pezeshki
Published: 2026-02-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.02366v1

Can Large language models (LLMs) learn to reason without any weight update and only through in-context learning (ICL)? ICL is strikingly sample-efficient, often learning from only a handful of demonstrations, but complex reasoning tasks typically demand many training examples to learn from. However, naively scaling ICL by adding more demonstrations breaks down at this scale: attention costs grow quadratically, performance saturates or degrades with longer contexts, and the approach remains a shallow form of learning. Due to these limitations, practitioners predominantly rely on in-weight learning (IWL) to induce reasoning. In this work, we show that by using Prefix Tuning, LLMs can learn to reason without overloading the context window and without any weight updates. We introduce $\textbf{ReasonCACHE}$, an instantiation of this mechanism that distills demonstrations into a fixed key-value cache. Empirically, across challenging reasoning benchmarks, including GPQA-Diamond, ReasonCACHE outperforms standard ICL and matches or surpasses IWL approaches. Further, it achieves this all while being more efficient across three key axes: data, inference cost, and trainable parameters. We also theoretically prove that ReasonCACHE can be strictly more expressive than low-rank weight update since the latter ties expressivity to input rank, whereas ReasonCACHE bypasses this constraint by directly injecting key-values into the attention mechanism. Together, our findings identify ReasonCACHE as a middle path between in-context and in-weight learning, providing a scalable algorithm for learning reasoning skills beyond the context window without modifying parameters. Our project page: https://reasoncache.github.io/

---

### SWE-Universe: Scale Real-World Verifiable Environments to Millions

Authors: Mouxiang Chen, Lei Zhang, Yunlong Feng, Xuwu Wang, Wenting Zhao, Ruisheng Cao, Jiaxi Yang, Jiawei Chen, Mingze Li, Zeyao Ma, Hao Ge, Zongmeng Zhang et al.
Published: 2026-02-02
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2602.02361v2

We propose SWE-Universe, a scalable and efficient framework for automatically constructing real-world software engineering (SWE) verifiable environments from GitHub pull requests (PRs). To overcome the prevalent challenges of automatic building, such as low production yield, weak verifiers, and prohibitive cost, our framework utilizes a building agent powered by an efficient custom-trained model. This agent employs iterative self-verification and in-loop hacking detection to ensure the reliable generation of high-fidelity, verifiable tasks. Using this method, we scale the number of real-world multilingual SWE environments to a million scale (807,693). We demonstrate the profound value of our environments through large-scale agentic mid-training and reinforcement learning. Finally, we applied this technique to Qwen3-Max-Thinking and achieved a score of 75.3% on SWE-Bench Verified. Our work provides both a critical resource and a robust methodology to advance the next generation of coding agents.

---

### SWE-Universe: Scale Real-World Verifiable Environments to Millions

Authors: Mouxiang Chen, Lei Zhang, Yunlong Feng, Xuwu Wang, Wenting Zhao, Ruisheng Cao, Jiaxi Yang, Jiawei Chen, Mingze Li, Zeyao Ma, Hao Ge, Zongmeng Zhang et al.
Published: 2026-02-02
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2602.02361v1

We propose SWE-Universe, a scalable and efficient framework for automatically constructing real-world software engineering (SWE) verifiable environments from GitHub pull requests (PRs). To overcome the prevalent challenges of automatic building, such as low production yield, weak verifiers, and prohibitive cost, our framework utilizes a building agent powered by an efficient custom-trained model. This agent employs iterative self-verification and in-loop hacking detection to ensure the reliable generation of high-fidelity, verifiable tasks. Using this method, we scale the number of real-world multilingual SWE environments to a million scale (807,693). We demonstrate the profound value of our environments through large-scale agentic mid-training and reinforcement learning. Finally, we applied this technique to Qwen3-Max-Thinking and achieved a score of 75.3% on SWE-Bench Verified. Our work provides both a critical resource and a robust methodology to advance the next generation of coding agents.

---

### Automated Multiple Mini Interview (MMI) Scoring

Authors: Ryan Huynh, Frank Guerin, Alison Callwood
Published: 2026-02-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.02360v1

Assessing soft skills such as empathy, ethical judgment, and communication is essential in competitive selection processes, yet human scoring is often inconsistent and biased. While Large Language Models (LLMs) have improved Automated Essay Scoring (AES), we show that state-of-the-art rationale-based fine-tuning methods struggle with the abstract, context-dependent nature of Multiple Mini-Interviews (MMIs), missing the implicit signals embedded in candidate narratives. We introduce a multi-agent prompting framework that breaks down the evaluation process into transcript refinement and criterion-specific scoring. Using 3-shot in-context learning with a large instruct-tuned model, our approach outperforms specialised fine-tuned baselines (Avg QWK 0.62 vs 0.32) and achieves reliability comparable to human experts. We further demonstrate the generalisability of our framework on the ASAP benchmark, where it rivals domain-specific state-of-the-art models without additional training. These findings suggest that for complex, subjective reasoning tasks, structured prompt engineering may offer a scalable alternative to data-intensive fine-tuning, altering how LLMs can be applied to automated assessment.

---

### Transfer Learning Through Conditional Quantile Matching

Authors: Yikun Zhang, Steven Wilkins-Reeves, Wesley Lee, Aude Hofleitner
Published: 2026-02-02
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.02358v1

We introduce a transfer learning framework for regression that leverages heterogeneous source domains to improve predictive performance in a data-scarce target domain. Our approach learns a conditional generative model separately for each source domain and calibrates the generated responses to the target domain via conditional quantile matching. This distributional alignment step corrects general discrepancies between source and target domains without imposing restrictive assumptions such as covariate or label shift. The resulting framework provides a principled and flexible approach to high-quality data augmentation for downstream learning tasks in the target domain. From a theoretical perspective, we show that an empirical risk minimizer (ERM) trained on the augmented dataset achieves a tighter excess risk bound than the target-only ERM under mild conditions. In particular, we establish new convergence rates for the quantile matching estimator that governs the transfer bias-variance tradeoff. From a practical perspective, extensive simulations and real data applications demonstrate that the proposed method consistently improves prediction accuracy over target-only learning and competing transfer learning methods.

---

### NAB: Neural Adaptive Binning for Sparse-View CT reconstruction

Authors: Wangduo Xie, Matthew B. Blaschko
Published: 2026-02-02
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.02356v2

Computed Tomography (CT) plays a vital role in inspecting the internal structures of industrial objects. Furthermore, achieving high-quality CT reconstruction from sparse views is essential for reducing production costs. While classic implicit neural networks have shown promising results for sparse reconstruction, they are unable to leverage shape priors of objects. Motivated by the observation that numerous industrial objects exhibit rectangular structures, we propose a novel Neural Adaptive Binning (NAB) method that effectively integrates rectangular priors into the reconstruction process. Specifically, our approach first maps coordinate space into a binned vector space. This mapping relies on an innovative binning mechanism based on differences between shifted hyperbolic tangent functions, with our extension enabling rotations around the input-plane normal vector. The resulting representations are then processed by a neural network to predict CT attenuation coefficients. This design enables end-to-end optimization of the encoding parameters -- including position, size, steepness, and rotation -- via gradient flow from the projection data, thus enhancing reconstruction accuracy. By adjusting the smoothness of the binning function, NAB can generalize to objects with more complex geometries. This research provides a new perspective on integrating shape priors into neural network-based reconstruction. Extensive experiments demonstrate that NAB achieves superior performance on two industrial datasets. It also maintains robust on medical datasets when the binning function is extended to more general expression. The code is available at https://github.com/Wangduo-Xie/NAB_CT_reconstruction.

---