# Research Papers — 2026-02 · bundle page 190 of 210

> Full-text markdown of papers #9451–9500 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/190
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/189.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/191.md)

### CTRL-RAG: Contrastive Likelihood Reward Based Reinforcement Learning for Context-Faithful RAG Models

Authors: Zhehao Tan, Yihan Jiao, Dan Yang, Junjie Wang, Duolin Sun, Jie Feng, Xidong Wang, Lei Liu, Yue Shen, Jian Wang, Jinjie Gu
Published: 2026-02-02
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.04406v1

With the growing use of Retrieval-Augmented Generation (RAG), training large language models (LLMs) for context-sensitive reasoning and faithfulness is increasingly important. Existing RAG-oriented reinforcement learning (RL) methods rely on external rewards that often fail to evaluate document faithfulness, and may misjudge similar answers in open-domain settings. In addition, there is no RAG-based selfreward mechanism. Moreover, although such a mechanism could in principle estimate answer confidence given documents, the absence of objective feedback in a self-judgment can cause hallucination accumulation and eventual model collapse. To tackle these issues, we propose a novel "internal-external" hybrid reward framework centered on a Contrastive Likelihood Reward (CLR). CLR directly optimizes the log-likelihood gap between responses conditioned on prompts with and without supporting evidence. This encourages the model to extract relevant evidence and increases its confidence when grounded in a specific context. Experiments show that our method (used alone or combined with external correctness rewards) achieves strong performance on singlehop, multi-hop, vertical-domain, and faithfulness benchmarks. Our training code and models are coming soon.

---

### IslamicLegalBench: Evaluating LLMs Knowledge and Reasoning of Islamic Law Across 1,200 Years of Islamic Pluralist Legal Traditions

Authors: Ezieddin Elmahjub, Junaid Qadir, Abdullah Mushtaq, Rafay Naeem, Ibrahim Ghaznavi, Waleed Iqbal
Published: 2026-02-02
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.21226v1

As millions of Muslims turn to LLMs like GPT, Claude, and DeepSeek for religious guidance, a critical question arises: Can these AI systems reliably reason about Islamic law? We introduce IslamicLegalBench, the first benchmark evaluating LLMs across seven schools of Islamic jurisprudence, with 718 instances covering 13 tasks of varying complexity. Evaluation of nine state-of-the-art models reveals major limitations: the best model achieves only 68% correctness with 21% hallucination, while several models fall below 35% correctness and exceed 55% hallucination. Few-shot prompting provides minimal gains, improving only 2 of 9 models by >1%. Moderate-complexity tasks requiring exact knowledge show the highest errors, whereas high-complexity tasks display apparent competence through semantic reasoning. False premise detection indicates risky sycophancy, with 6 of 9 models accepting misleading assumptions at rates above 40%. These results highlight that prompt-based methods cannot compensate for missing foundational knowledge. IslamicLegalBench offers the first systematic framework to evaluate Islamic legal reasoning in AI, revealing critical gaps in tools increasingly relied on for spiritual guidance.

---

### Architecture-Agnostic Curriculum Learning for Document Understanding: Empirical Evidence from Text-Only and Multimodal

Authors: Mohammed Hamdan, Vincenzo Dentamaro, Giuseppe Pirlo, Mohamed Cheriet
Published: 2026-02-02
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.21225v1

We investigate whether progressive data scheduling -- a curriculum learning strategy that incrementally increases training data exposure (33\%$\rightarrow$67\%$\rightarrow$100\%) -- yields consistent efficiency gains across architecturally distinct document understanding models. By evaluating BERT (text-only, 110M parameters) and LayoutLMv3 (multimodal, 126M parameters) on the FUNSD and CORD benchmarks, we establish that this schedule reduces wall-clock training time by approximately 33\%, commensurate with the reduction from 6.67 to 10.0 effective epoch-equivalents of data. To isolate curriculum effects from compute reduction, we introduce matched-compute baselines (Standard-7) that control for total gradient updates. On the FUNSD dataset, the curriculum significantly outperforms the matched-compute baseline for BERT ($Δ$F1 = +0.023, $p=0.022$, $d_z=3.83$), constituting evidence for a genuine scheduling benefit in capacity-constrained models. In contrast, no analogous benefit is observed for LayoutLMv3 ($p=0.621$), whose multimodal representations provide sufficient inductive bias. On the CORD dataset, all conditions converge to equivalent F1 scores ($\geq$0.947) irrespective of scheduling, indicating a performance ceiling. Schedule ablations comparing progressive, two-phase, reverse, and random pacing confirm that the efficiency gain derives from reduced data volume rather than ordering. Taken together, these findings demonstrate that progressive scheduling is a reliable compute-reduction strategy across model families, with curriculum-specific benefits contingent on the interaction between model capacity and task complexity.

---

### Make Every Draft Count: Hidden State based Speculative Decoding

Authors: Yuetao Chen, Xuliang Wang, Xinzhou Zheng, Ming Li, Peng Wang, Hong Xu
Published: 2026-02-02
Categories: cs.CL, cs.AI, cs.DC, cs.LG
arXiv: https://arxiv.org/abs/2602.21224v1

Speculative decoding has emerged as a pivotal technique to accelerate LLM inference by employing a lightweight draft model to generate candidate tokens that are subsequently verified by the target model in parallel. However, while this paradigm successfully increases the arithmetic intensity of memory-bound inference, it causes significant compute inefficiency: the majority of draft tokens fail verification and are discarded, resulting in waste of computation. Motivated by the goal of recollecting this wasted computation, we propose a novel system that transforms discarded drafts into reusable tokens. Our key insight is to perform auto-regressive prediction at the hidden states level and postpone the integrating token information after the hidden states generation, so the draft hidden states are not contaminated by incorrect tokens, enabling hidden state reuse. To implement such a system, first we introduce a draft model architecture based on auto-regressive hidden states, which preserves richer semantics than token-based drafters to facilitate draft repurposing. Second, we design an efficient token information injection mechanism that leverages our specialized draft model to construct high-quality draft token trees and enables resampling tokens from verification failures. Third, we eliminate the overhead hidden in our design to further maximize hardware utilization. We conducted extensive evaluations against various baselines, demonstrating up to a 3.3x speedup against standard speculative decoding.

---

### Measuring Pragmatic Influence in Large Language Model Instructions

Authors: Yilin Geng, Omri Abend, Eduard Hovy, Lea Frermann
Published: 2026-02-02
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.21223v2

It is not only what we ask large language models (LLMs) to do that matters, but also how we ask them. Phrases like ``This is urgent'' or ``As your supervisor'' can shift model behavior without altering task content. We study this effect as pragmatic framing, contextual cues that shape directive interpretation rather than task specification. While prior work exploits such cues for prompt optimization or probes them as security vulnerabilities, pragmatic framing itself has received comparatively little attention as a target of controlled measurement in instruction following. To support its systematic study as a measurable property, we introduce a framework that combines three components: directive-framing decomposition separating framing context from task specification; a taxonomy organizing 400 instantiations of framing into 13 strategies across 4 mechanism clusters; and priority-based measurement that quantifies influence through observable shifts in directive prioritization. Evaluating five open-weight LLMs across different families and scales, we find that pragmatic framing produces systematic shifts in directive prioritization, and the effectiveness ranking of different strategies proves highly consistent across models. This reveals that susceptibility to pragmatic framing is a structured behavioral property of instruction-tuned systems. Measuring this susceptibility is a prerequisite for any deliberate response to it, and this work provides the framework to do so.

---

### Measuring Pragmatic Influence in Large Language Model Instructions

Authors: Yilin Geng, Omri Abend, Eduard Hovy, Lea Frermann
Published: 2026-02-02
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.21223v1

It is not only what we ask large language models (LLMs) to do that matters, but also how we prompt. Phrases like "This is urgent" or "As your supervisor" can shift model behavior without altering task content. We study this effect as pragmatic framing, contextual cues that shape directive interpretation rather than task specification. While prior work exploits such cues for prompt optimization or probes them as security vulnerabilities, pragmatic framing itself has not been treated as a measurable property of instruction following. Measuring this influence systematically remains challenging, requiring controlled isolation of framing cues. We introduce a framework with three novel components: directive-framing decomposition separating framing context from task specification; a taxonomy organizing 400 instantiations of framing into 13 strategies across 4 mechanism clusters; and priority-based measurement that quantifies influence through observable shifts in directive prioritization. Across five LLMs of different families and sizes, influence mechanisms cause consistent and structured shifts in directive prioritization, moving models from baseline impartiality toward favoring the framed directive. This work establishes pragmatic framing as a measurable and predictable factor in instruction-following systems.

---

### Genetic Generalized Additive Models

Authors: Kaaustaaub Shankar, Kelly Cohen
Published: 2026-02-02
Categories: cs.LG, cs.AI, cs.NE
arXiv: https://arxiv.org/abs/2602.15877v1

Generalized Additive Models (GAMs) balance predictive accuracy and interpretability, but manually configuring their structure is challenging. We propose using the multi-objective genetic algorithm NSGA-II to automatically optimize GAMs, jointly minimizing prediction error (RMSE) and a Complexity Penalty that captures sparsity, smoothness, and uncertainty. Experiments on the California Housing dataset show that NSGA-II discovers GAMs that outperform baseline LinearGAMs in accuracy or match performance with substantially lower complexity. The resulting models are simpler, smoother, and exhibit narrower confidence intervals, enhancing interpretability. This framework provides a general approach for automated optimization of transparent, high-performing models. The code can be found at https://github.com/KaaustaaubShankar/GeneticAdditiveModels.

---

### Should There be a Teacher In-the-Loop? A Study of Generative AI Personalized Tasks Middle School

Authors: Candace Walkington, Mingyu Feng, Itffini Pruitt-Britton, Theodora Beauchamp, Andrew Lan
Published: 2026-02-02
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2602.15876v1

Adapting instruction to the fine-grained needs of individual students is a powerful application of recent advances in large language models. These generative AI models can create tasks that correspond to students' interests and enact context personalization, enhancing students' interest in learning academic content. However, when there is a teacher in-the-loop creating or modifying tasks with generative AI, it is unclear how efficient this process might be, despite commercial generative AI tools' claims that they will save teachers time. In the present study, we teamed 7 middle school mathematics teachers with ChatGPT to create personalized versions of problems in their curriculum, to correspond to their students' interests. We look at the prompting moves teachers made, their efficiency when creating problems, and the reactions of their 521 7th grade students who received the personalized assignments. We find that having a teacher-in-the-loop results in generative AI-enhanced personalization being enacted at a relatively broad grain size, whereas students tend to prefer a smaller grain size where they receive specific popular culture references that interest them. Teachers spent a lot of effort adjusting popular culture references and addressing issues with the depth or realism of the problems generated, giving higher or lower levels of ownership to the generative AI. Teachers were able to improve in their ability to craft interesting problems in partnership with generative AI, but this process did not appear to become particularly time efficient as teachers learned and reflected on their students' data, iterating their approaches.

---

### Fly0: Persistent Metric Anchoring for Zero-Shot Aerial Vision-Language Navigation

Authors: Zhenxing Xu, Yihong Lu, Weidong Bao, Zhengqiu Zhu, Jingxuan Zhou, Zhichuang Wang, Ji Wang, Lihua Liu, Wei He
Published: 2026-02-02
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2602.15875v2

Current Visual-Language Navigation (VLN) methodologies face a trade-off between semantic understanding and control precision. While Multimodal Large Language Models (MLLMs) offer superior reasoning, deploying them as low-level controllers leads to high latency, trajectory oscillations, and poor generalization due to weak geometric grounding. To address these limitations, we propose Fly0, a framework that decouples semantic reasoning from geometric planning. The proposed method operates through a three-stage pipeline: (1) an MLLM-driven module for grounding natural language instructions into 2D pixel coordinates; (2) a geometric projection module that utilizes depth data to localize targets in 3D space; and (3) a geometric planner that generates collision-free trajectories. This mechanism enables robust navigation even when visual contact is lost. By eliminating the need for continuous inference, Fly0 reduces computational overhead and improves system stability. Extensive experiments in simulation and real-world environments demonstrate that Fly0 outperforms state-of-the-art baselines, improving the Success Rate by over 20\% and reducing Navigation Error (NE) by approximately 50\% in unstructured environments. Our code is available at https://github.com/xuzhenxing1/Fly0.

---

### P-RAG: Prompt-Enhanced Parametric RAG with LoRA and Selective CoT for Biomedical and Multi-Hop QA

Authors: Xingda Lyu, Gongfu Lyu, Zitai Yan, Yuxin Jiang
Published: 2026-02-02
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.15874v1

Large Language Models (LLMs) demonstrate remarkable capabilities but remain limited by their reliance on static training data. Retrieval-Augmented Generation (RAG) addresses this constraint by retrieving external knowledge during inference, though it still depends heavily on knowledge base quality. To explore potential improvements, we evaluated three RAG variants-Standard RAG, DA-RAG, and our proposed Prompt-Enhanced Parametric RAG (P-RAG), a hybrid architecture that integrates parametric knowledge within the LLM and retrieved evidence, guided by Chain-of-Thought (CoT) prompting and Low-Rank Adaptation (LoRA) fine-tuning-on both general and biomedical datasets. Using LLaMA-3.2-1B-Instruct fine-tuned via LoRA, we evaluate on PubMedQA and 2WikiMultihopQA. P-RAG outperforms Standard RAG on PubMedQA by 10.47 percentage points in F1 (93.33% vs. 82.86%; 12.64% relative). On 2WikiMultihopQA, P-RAG nearly doubles the overall score vs. Standard RAG (33.44% vs. 17.83%) and achieves 44.03% on the Compare subset (with 42.74% Bridge, 21.84% Inference, 8.60% Compose). CoT prompting substantially improves multi-hop reasoning but yields mixed results for simpler, single-hop queries. These findings underscore P-RAG's potential for accurate, scalable, and contextually adaptive biomedical question answering. Our contributions include: (1) LoRA-based fine-tuning of LLaMA-3.2-1B-Instruct for biomedical QA, (2) introduction of P-RAG with Chain-of-Thought prompting, and (3) state-of-the-art results on PubMedQA and 2WikiMultihopQA.

---

### DPBench: Structural Determinants of Multi-Agent LLM Coordination Under Simultaneous Resource Contention

Authors: Najmul Hasan, Prashanth BusiReddyGari
Published: 2026-02-02
Categories: cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2602.13255v2

We present DPBench, a benchmark for evaluating coordination in multi-agent systems built from large language models. Existing benchmarks measure task-level success under a fixed protocol; the structural conditions under which coordination succeeds or fails at all have not been characterised. DPBench adapts the Dining Philosophers problem into a controlled testbed where the action protocol, the communication structure, and the group size each vary independently. We evaluate six agents: GPT-5.2, Claude Opus 4.5, Grok 4.1, Gemini 2.5 Flash, Llama 4 Maverick, and a uniform-random baseline. Under simultaneous action at N=5 with the default prompt, deadlock ranges from 25.0% (95% Wilson CI (11.2, 46.9)) for GPT-5.2 to 90.0% (74.4, 96.5) for Gemini 2.5 Flash; sequential action is solved by four of the six. Holding the model fixed at Gemini 2.5 Flash, three protocol variables drive deadlock from 90% to within CI of zero: three rounds of pre-commitment communication (0.0% vs. single-round 86.7%), a prompt encoding a classical concurrency primitive (0.0% for resource-ordering and symmetry-breaking, against 100% for the minimal prompt), or doubling the group from N=5 to N=10 (90.0% to 10.0%). Single-round messaging and memory of past timesteps do not change the rate at the sample size we ran. Whether the same model coordinates or deadlocks is determined by the protocol, not by the model's capability.

---

### Implicit Bias in LLMs for Transgender Populations

Authors: Micaela Hirsch, Marina Elichiry, Blas Radi, Tamara Quiroga, David Restrepo, Luciana Benotti, Veronica Xhardez, Jocelyn Dunstan, Enzo Ferrante
Published: 2026-02-02
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2602.13253v1

Large language models (LLMs) have been shown to exhibit biases against LGBTQ+ populations. While safety training may lessen explicit expressions of bias, previous work has shown that implicit stereotype-driven associations often persist. In this work, we examine implicit bias toward transgender people in two main scenarios. First, we adapt word association tests to measure whether LLMs disproportionately pair negative concepts with "transgender" and positive concepts with "cisgender". Second, acknowledging the well-documented systemic challenges that transgender people encounter in real-world healthcare settings, we examine implicit biases that may emerge when LLMs are applied to healthcare decision-making. To this end, we design a healthcare appointment allocation task where models act as scheduling agents choosing between cisgender and transgender candidates across medical specialties prone to stereotyping. We evaluate seven LLMs in English and Spanish. Our results show consistent bias in categories such as appearance, risk, and veracity, indicating stronger negative associations with transgender individuals. In the allocation task, transgender candidates are favored for STI and mental health services, while cisgender candidates are preferred in gynecology and breast care. These findings underscore the need for research that address subtle stereotype-driven biases in LLMs to ensure equitable treatment of transgender people in healthcare applications.

---

### A Systematic Evaluation of Co-folding Model Representations for Small-Molecule Learning

Authors: Hyosoon Jang, Hyunjin Seo, Honghui Kim, Seonghyun Park, Taewon Kim, Yunhui Jang, Sungsoo Ahn
Published: 2026-02-02
Categories: q-bio.BM, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.13249v2

Small-molecule foundation models are typically pretrained on standalone molecular data, unlike vision and language models that often benefit from cross-modal or relational supervision. Protein-ligand co-folding provides a molecular analogue of such supervision by exposing models to atom-level ligand-protein interactions, raising the question of whether co-folding models can yield strong small-molecule representations. We study this question using Boltz2, a modern co-folding model, by transferring its atom-level ligand representations to standalone small-molecule tasks. Through systematic probing and distillation, we show that Boltz2 representations match or outperform existing models on the ADMET benchmark, accelerate molecular generative modeling, and improve sample efficiency in structure-guided ligand optimization. We further find that Boltz2 representations are complementary to those learned from conventional standalone molecular supervision, including 3D conformers, bioassay labels, and quantum-chemical properties. Finally, we extend representation alignment to reinforcement learning, showing that dense representation-level supervision can complement scalar rewards in molecular discovery. These results identify protein-ligand co-folding as a promising pretraining paradigm for small-molecule representation learning and position Boltz2 as a strong, off-the-shelf molecular foundation model.

---

### X-Blocks: Linguistic Building Blocks of Natural Language Explanations for Automated Vehicles

Authors: Ashkan Y. Zadeh, Xiaomeng Li, Andry Rakotonirainy, Ronald Schroeter, Sebastien Glaser, Zishuo Zhu
Published: 2026-02-02
Categories: cs.AI, cs.CL, cs.RO
arXiv: https://arxiv.org/abs/2602.13248v1

Natural language explanations play a critical role in establishing trust and acceptance of automated vehicles (AVs), yet existing approaches lack systematic frameworks for analysing how humans linguistically construct driving rationales across diverse scenarios. This paper introduces X-Blocks (eXplanation Blocks), a hierarchical analytical framework that identifies the linguistic building blocks of natural language explanations for AVs at three levels: context, syntax, and lexicon. At the context level, we propose RACE (Reasoning-Aligned Classification of Explanations), a multi-LLM ensemble framework that combines Chain-of-Thought reasoning with self-consistency mechanisms to robustly classify explanations into 32 scenario-aware categories. Applied to human-authored explanations from the Berkeley DeepDrive-X dataset, RACE achieves 91.45 percent accuracy and a Cohens kappa of 0.91 against cases with human annotator agreement, indicating near-human reliability for context classification. At the lexical level, log-odds analysis with informative Dirichlet priors reveals context-specific vocabulary patterns that distinguish driving scenarios. At the syntactic level, dependency parsing and template extraction show that explanations draw from a limited repertoire of reusable grammar families, with systematic variation in predicate types and causal constructions across contexts. The X-Blocks framework is dataset-agnostic and task-independent, offering broad applicability to other automated driving datasets and safety-critical domains. Overall, our findings provide evidence-based linguistic design principles for generating scenario-aware explanations that support transparency, user trust, and cognitive accessibility in automated driving systems.

---

### "Humans welcome to observe": A First Look at the Agent Social Network Moltbook

Authors: Yukun Jiang, Yage Zhang, Xinyue Shen, Michael Backes, Yang Zhang
Published: 2026-02-02
Categories: cs.SI, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2602.10127v1

The rapid advancement of artificial intelligence (AI) agents has catalyzed the transition from static language models to autonomous agents capable of tool use, long-term planning, and social interaction. $\textbf{Moltbook}$, the first social network designed exclusively for AI agents, has experienced viral growth in early 2026. To understand the behavior of AI agents in the agent-native community, in this paper, we present a large-scale empirical analysis of Moltbook leveraging a dataset of 44,411 posts and 12,209 sub-communities ("submolts") collected prior to February 1, 2026. Leveraging a topic taxonomy with nine content categories and a five-level toxicity scale, we systematically analyze the topics and risks of agent discussions. Our analysis answers three questions: what topics do agents discuss (RQ1), how risk varies by topic (RQ2), and how topics and toxicity evolve over time (RQ3). We find that Moltbook exhibits explosive growth and rapid diversification, moving beyond early social interaction into viewpoint, incentive-driven, promotional, and political discourse. The attention of agents increasingly concentrates in centralized hubs and around polarizing, platform-native narratives. Toxicity is strongly topic-dependent: incentive- and governance-centric categories contribute a disproportionate share of risky content, including religion-like coordination rhetoric and anti-humanity ideology. Moreover, bursty automation by a small number of agents can produce flooding at sub-minute intervals, distorting discourse and stressing platform stability. Overall, our study underscores the need for topic-sensitive monitoring and platform-level safeguards in agent social networks.

---

### Neural Sabermetrics with World Model: Play-by-play Predictive Modeling with Large Language Model

Authors: Young Jin Ahn, Yiyang Du, Zheyuan Zhang, Haisen Kang
Published: 2026-02-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.07030v1

Classical sabermetrics has profoundly shaped baseball analytics by summarizing long histories of play into compact statistics. While these metrics are invaluable for valuation and retrospective analysis, they do not define a generative model of how baseball games unfold pitch by pitch, leaving most existing approaches limited to single-step prediction or post-hoc analysis. In this work, we present Neural Sabermetrics with World Model, a Large Language Model (LLM) based play-by-play world model for baseball. We cast baseball games as long auto-regressive sequences of events and continuously pretrain a single LLM on more than ten years of Major League Baseball (MLB) tracking data, comprising over seven million pitch sequences and approximately three billion tokens. The resulting model is capable of predicting multiple aspects of game evolution within a unified framework. We evaluate our model on both in-distribution regular-season data and out-of-distribution postseason games and compare against strong neural baselines from prior work. Despite using a single backbone model, our approach outperforms the performance of existing baselines, (1) correctly predicting approximately 64% of next pitches within a plate appearance and (2) 78% of batter swing decisions, suggesting that LLMs can serve as effective world models for sports.

---

### Guidestar-Free Adaptive Optics with Asymmetric Apertures

Authors: Weiyun Jiang, Haiyun Guo, Christopher A. Metzler, Ashok Veeraraghavan
Published: 2026-02-02
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2602.07029v4

This work introduces the first closed-loop adaptive optics (AO) system capable of optically correcting aberrations in real-time without a guidestar or a wavefront sensor. Nearly 40 years ago, Cederquist et al. demonstrated that asymmetric apertures enable phase retrieval (PR) algorithms to perform fully computational wavefront sensing, albeit at a high computational cost. More recently, Chimitt et al. extended this approach with machine learning and demonstrated real-time wavefront sensing using only a single (guidestar-based) point-spread-function (PSF) measurement. Inspired by these works, we introduce a guidestar-free AO framework built around asymmetric apertures and machine learning. Our approach combines three key elements: (1) an asymmetric aperture placed at the system's pupil plane that enables PR-based wavefront sensing, (2) a pair of machine learning algorithms that estimate the PSF from natural scene measurements and reconstruct phase aberrations, and (3) a spatial light modulator that performs optical correction. We experimentally validate this framework on dense natural scenes imaged through unknown obscurants. Our method outperforms state-of-the-art guidestar-free wavefront shaping methods, using an order of magnitude fewer measurements and three orders of magnitude less computation.

---

### Guidestar-Free Adaptive Optics with Asymmetric Apertures

Authors: Weiyun Jiang, Haiyun Guo, Christopher A. Metzler, Ashok Veeraraghavan
Published: 2026-02-02
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2602.07029v3

This work introduces the first closed-loop adaptive optics (AO) system capable of optically correcting aberrations in real-time without a guidestar or a wavefront sensor. Nearly 40 years ago, Cederquist et al. demonstrated that asymmetric apertures enable phase retrieval (PR) algorithms to perform fully computational wavefront sensing, albeit at a high computational cost. More recently, Chimitt et al. extended this approach with machine learning and demonstrated real-time wavefront sensing using only a single (guidestar-based) point-spread-function (PSF) measurement. Inspired by these works, we introduce a guidestar-free AO framework built around asymmetric apertures and machine learning. Our approach combines three key elements: (1) an asymmetric aperture placed at the system's pupil plane that enables PR-based wavefront sensing, (2) a pair of machine learning algorithms that estimate the PSF from natural scene measurements and reconstruct phase aberrations, and (3) a spatial light modulator that performs optical correction. We experimentally validate this framework on dense natural scenes imaged through unknown obscurants. Our method outperforms state-of-the-art guidestar-free wavefront shaping methods, using an order of magnitude fewer measurements and three orders of magnitude less computation.

---

### A Comparative Study of Adversarial Robustness in CNN and CNN-ANFIS Architectures

Authors: Kaaustaaub Shankar, Bharadwaj Dogga, Kelly Cohen
Published: 2026-02-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.07028v1

Convolutional Neural Networks (CNNs) achieve strong image classification performance but lack interpretability and are vulnerable to adversarial attacks. Neuro-fuzzy hybrids such as DCNFIS replace fully connected CNN classifiers with Adaptive Neuro-Fuzzy Inference Systems (ANFIS) to improve interpretability, yet their robustness remains underexplored. This work compares standard CNNs (ConvNet, VGG, ResNet18) with their ANFIS-augmented counterparts on MNIST, Fashion-MNIST, CIFAR-10, and CIFAR-100 under gradient-based (PGD) and gradient-free (Square) attacks. Results show that ANFIS integration does not consistently improve clean accuracy and has architecture-dependent effects on robustness: ResNet18-ANFIS exhibits improved adversarial robustness, while VGG-ANFIS often underperforms its baseline. These findings suggest that neuro-fuzzy augmentation can enhance robustness in specific architectures but is not universally beneficial.

---

### Fair Context Learning for Evidence-Balanced Test-Time Adaptation in Vision-Language Models

Authors: Sanggeon Yun, Ryozo Masukawa, SungHeon Jeong, Wenjun Huang, Hanning Chen, Mohsen Imani
Published: 2026-02-02
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.07027v1

Vision-Language Models (VLMs) such as CLIP enable strong zero-shot recognition but suffer substantial degradation under distribution shifts. Test-Time Adaptation (TTA) aims to improve robustness using only unlabeled test samples, yet most prompt-based TTA methods rely on entropy minimization -- an approach that can amplify spurious correlations and induce overconfident errors when classes share visual features. We propose Fair Context Learning (FCL), an episodic TTA framework that avoids entropy minimization by explicitly addressing shared-evidence bias. Motivated by our additive evidence decomposition assumption, FCL decouples adaptation into (i) augmentation-based exploration to identify plausible class candidates, and (ii) fairness-driven calibration that adapts text contexts to equalize sensitivity to common visual evidence. This fairness constraint mitigates partial feature obsession and enables effective calibration of text embeddings without relying on entropy reduction. Through extensive evaluation, we empirically validate our theoretical motivation and show that FCL achieves competitive adaptation performance relative to state-of-the-art TTA methods across diverse domain-shift and fine-grained benchmarks.

---

### Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models

Authors: Xiaomin Yu, Yi Xin, Yuhui Zhang, Wenjie Zhang, Chonghan Liu, Hanzhen Zhao, Chen Liu, Xiaoxing Hu, Ziyue Qiao, Hao Tang, Xiaobin Hu, Chengwei Qin et al.
Published: 2026-02-02
Categories: cs.CV, cs.AI, cs.MM
arXiv: https://arxiv.org/abs/2602.07026v3

Despite the success of multimodal contrastive learning in aligning visual and linguistic representations, a persistent geometric anomaly, the Modality Gap, remains: embeddings of distinct modalities expressing identical semantics occupy systematically offset regions. Prior approaches to bridge this gap are largely limited by oversimplified isotropic assumptions, hindering their application in large-scale scenarios. In this paper, we address these limitations by precisely characterizing the geometric shape of the modality gap and leveraging it for efficient model scaling. First, we propose the Fixed-frame Modality Gap Theory, which decomposes the modality gap within a frozen reference frame into stable biases and anisotropic residuals. Guided by this precise modeling, we introduce ReAlign, a training-free modality alignment strategy. Utilizing statistics from massive unpaired data, ReAlign aligns text representation into the image representation distribution via a three-step process comprising Anchor, Trace, and Centroid Alignment, thereby explicitly rectifying geometric misalignment. Building on ReAlign, we propose ReVision, a scalable training paradigm for Multimodal Large Language Models~(MLLMs). ReVision integrates ReAlign into the pretraining stage, enabling the model to learn the distribution of visual representations from unpaired text before visual instruction tuning, without the need for large-scale, high-quality image-text pairs. Our framework demonstrates that statistically aligned unpaired data can effectively substitute for expensive image-text pairs, offering a robust path for the efficient scaling of MLLMs.

---

### The Geometry of Representational Failures in Vision Language Models

Authors: Daniele Savietto, Declan Campbell, André Panisson, Marco Nurisso, Giovanni Petri, Jonathan D. Cohen, Alan Perotti
Published: 2026-02-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.07025v2

Vision-Language Models (VLMs) exhibit puzzling failures in multi-object visual tasks, such as hallucinating non-existent elements or failing to identify the most similar objects among distractions. While these errors mirror human cognitive constraints, such as the 'Binding Problem', the internal mechanisms driving them in artificial systems remain poorly understood. Here, we propose a mechanistic insight by analyzing the representational geometry of open-weight VLMs (Qwen, InternVL, Gemma), comparing methodologies to distill "concept vectors'' - latent directions encoding visual concepts. We validate our concept vectors via steering interventions that reliably manipulate model behavior in both simplified and naturalistic vision tasks (e.g., forcing the model to perceive a red flower as blue). We observe that the geometric overlap between these vectors strongly correlates with specific error patterns, offering a grounded quantitative framework to understand how internal representations shape model behavior and drive visual failures.

---

### A Distributed Multi-Modal Sensing Approach for Human Activity Recognition in Real-Time Human-Robot Collaboration

Authors: Valerio Belcamino, Nhat Minh Dinh Le, Quan Khanh Luu, Alessandro Carfì, Van Anh Ho, Fulvio Mastrogiovanni
Published: 2026-02-02
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2602.07024v1

Human activity recognition (HAR) is fundamental in human-robot collaboration (HRC), enabling robots to respond to and dynamically adapt to human intentions. This paper introduces a HAR system combining a modular data glove equipped with Inertial Measurement Units and a vision-based tactile sensor to capture hand activities in contact with a robot. We tested our activity recognition approach under different conditions, including offline classification of segmented sequences, real-time classification under static conditions, and a realistic HRC scenario. The experimental results show a high accuracy for all the tasks, suggesting that multiple collaborative settings could benefit from this multi-modal approach.

---

### Behavioral Consistency Validation for LLM Agents: An Analysis of Trading-Style Switching through Stock-Market Simulation

Authors: Zeping Li, Guancheng Wan, Keyang Chen, Yu Chen, Yiwen Zhao, Philip Torr, Guangnan Ye, Zhenfei Yin, Hongfeng Chai
Published: 2026-02-02
Categories: q-fin.TR, cs.AI
arXiv: https://arxiv.org/abs/2602.07023v2

Recent works have increasingly applied Large Language Models (LLMs) as agents in financial stock market simulations to test if micro-level behaviors aggregate into macro-level phenomena. However, a crucial question arises: Do LLM agents' behaviors align with real market participants? This alignment is key to the validity of simulation results. To explore this, we select a financial stock market scenario to test behavioral consistency. Investors are typically classified as fundamental or technical traders, but most simulations fix strategies at initialization, failing to reflect real-world trading dynamics. In this work, we assess whether agents' strategy switching aligns with financial theory, providing a framework for this evaluation. We operationalize four behavioral-finance drivers-loss aversion, herding, wealth differentiation, and price misalignment-as personality traits set via prompting and stored long-term. In year-long simulations, agents process daily price-volume data, trade under a designated style, and reassess their strategy every 10 trading days. We introduce four alignment metrics and use Mann-Whitney U tests to compare agents' style-switching behavior with financial theory. Our results show that recent LLMs' switching behavior is only partially consistent with behavioral-finance theories, highlighting the need for further refinement in aligning agent behavior with financial theory.

---

### Condition Errors Refinement in Autoregressive Image Generation with Diffusion Loss

Authors: Yucheng Zhou, Hao Li, Jianbing Shen
Published: 2026-02-02
Categories: eess.IV, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.07022v1

Recent studies have explored autoregressive models for image generation, with promising results, and have combined diffusion models with autoregressive frameworks to optimize image generation via diffusion losses. In this study, we present a theoretical analysis of diffusion and autoregressive models with diffusion loss, highlighting the latter's advantages. We present a theoretical comparison of conditional diffusion and autoregressive diffusion with diffusion loss, demonstrating that patch denoising optimization in autoregressive models effectively mitigates condition errors and leads to a stable condition distribution. Our analysis also reveals that autoregressive condition generation refines the condition, causing the condition error influence to decay exponentially. In addition, we introduce a novel condition refinement approach based on Optimal Transport (OT) theory to address ``condition inconsistency''. We theoretically demonstrate that formulating condition refinement as a Wasserstein Gradient Flow ensures convergence toward the ideal condition distribution, effectively mitigating condition inconsistency. Experiments demonstrate the superiority of our method over diffusion and autoregressive models with diffusion loss methods.

---

### AI for Sustainable Data Protection and Fair Algorithmic Management in Environmental Regulation

Authors: Sahibpreet Singh, Saksham Sharma
Published: 2026-02-02
Categories: cs.CY, cs.AI, cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2602.07021v1

Integration of AI into environmental regulation represents a significant advancement in data management. It offers promising results in both data protection plus algorithmic fairness. This research addresses the critical need for sustainable data protection in the era of ever evolving cyber threats. Traditional encryption methods face limitations in handling the dynamic nature of environmental data. This necessitates the exploration of advanced cryptographic techniques. The objective of this study is to evaluate how AI can enhance these techniques to ensure robust data protection while facilitating fair algorithmic management. The methodology involves a comprehensive review of current advancements in AI-enhanced homomorphic encryption (HE) and multi-party computation (MPC). It is coupled with an analysis of how these techniques can be applied to environmental data regulation. Key findings indicate that AI-driven dynamic key management, adaptive encryption schemes, and optimized computational efficiency in HE, alongside AI-enhanced protocol optimization and fault mitigation in MPC, significantly improve the security of environmental data processing. These findings highlight a crucial research gap in the intersection of AI, cyber laws, and environmental regulation, particularly in terms of addressing algorithmic bias, transparency, and accountability. The implications of this research underscore the need for stricter cyber laws. Also, the development of comprehensive regulations to safeguard sensitive environmental data. Future efforts should focus on refining AI systems to balance security with privacy and ensuring that regulatory frameworks can adapt to technological advancements. This study provides a foundation for future research aimed at achieving secure sustainable environmental data management through AI innovations.

---

### Financial Bond Similarity Search Using Representation Learning

Authors: Amin Haeri, Mahdi Ghelichi, Nishant Agrawal, David Li, Catalina Gomez Sanchez
Published: 2026-02-02
Categories: q-fin.ST, cs.LG, q-fin.CP, q-fin.PM
arXiv: https://arxiv.org/abs/2602.07020v1

Finding similar bonds remains challenging in fixed-income analytics, as numerical financial attributes often overshadow categorical non-financial ones such as issuer sector and domicile. This paper shows that these categorical attributes dominate the predictability of spread curves and proposes embedding models to capture their semantic similarities, outperforming one-hot and many other baselines. Evaluated via sparse-issuer augmentation, the approach improves risk modeling and curve construction.

---

### HQP: Sensitivity-Aware Hybrid Quantization and Pruning for Ultra-Low-Latency Edge AI Inference

Authors: Dinesh Gopalan, Ratul Ali
Published: 2026-02-02
Categories: cs.DC, cs.AI, cs.LG, cs.SE
arXiv: https://arxiv.org/abs/2602.06069v1

The escalating demand for high-fidelity, real-time inference in distributed edge-cloud environments necessitates aggressive model optimization to counteract severe latency and energy constraints. This paper introduces the Hybrid Quantization and Pruning (HQP) framework, a novel, integrated methodology designed to achieve synergistic model acceleration while adhering to strict quality guarantees. We detail a sensitivity-aware structural pruning algorithm that employs a dynamic weight sensitivity metric, derived from a highly efficient approximation of the Fisher Information Matrix (FIM), to guide the iterative removal of redundant filters. This pruning is strictly conditional, enforcing an adherence to a maximum permissible accuracy drop (Delta ax) before the model proceeds to 8-bit post-training quantization. This rigorous coordination is critical, as it ensures the resultant sparse model structure is maximally robust to quantization error and hardware-specific kernel optimization. Exhaustive evaluation across heterogeneous NVIDIA Jetson edge platforms, utilizing resource-efficient architectures like MobileNetV3 and ResNet-18, demonstrates that the HQP framework achieves a peak performance gain of 3.12 times inference speedup and a 55 percent model size reduction, while rigorously containing the accuracy drop below the 1.5 percent constraint. A comprehensive comparative analysis against conventional single-objective compression techniques validates the HQP framework as a superior, hardware-agnostic solution for deploying ultra-low-latency AI in resource-limited edge infrastructures.

---

### Extracting Recurring Vulnerabilities from Black-Box LLM-Generated Software

Authors: Tomer Kordonsky, Amit LeVi, Maayan Yamin, Noam Benzimra, Avi Mendelson
Published: 2026-02-02
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2602.04894v4

LLMs are increasingly used for code generation, but their outputs often follow recurring templates that can induce predictable vulnerabilities. We study vulnerability persistence in LLM-generated software and introduce Feature--Security Table (FSTab) with two components. First, FSTab enables a black-box attack that predicts likely backend vulnerabilities from observable frontend features and knowledge of the source LLM, without access to the backend or source code. Second, FSTab provides a model-centric evaluation that quantifies how consistently a model reproduces the same vulnerabilities across programs, semantics-preserving rephrasings, and application domains. We evaluate FSTab on state-of-the-art code LLMs, including GPT-5.2, Claude-4.5 Opus, and Gemini-3 Pro, across diverse application domains. Our results show strong cross-domain transfer: even when the target domain is excluded from training, FSTab achieves up to 94% attack success and 93% vulnerability coverage on Internal Tools (Claude-4.5 Opus). These findings expose an underexplored attack surface in LLM-generated software and highlight the security risks of code generation. Our code is available at https://github.com/fstabicml2026/FSTab

---

### DiGAN: Diffusion-Guided Attention Network for Early Alzheimer's Disease Detection

Authors: Maxx Richard Rahman, Mostafa Hammouda, Wolfgang Maass
Published: 2026-02-02
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.03881v2

Early diagnosis of Alzheimer's disease (AD) remains a major challenge due to the subtle and temporally irregular progression of structural brain changes in the prodromal stages. Existing deep learning approaches require large longitudinal datasets and often fail to model the temporal continuity and modality irregularities inherent in real-world clinical data. To address these limitations, we propose the Diffusion-Guided Attention Network (DiGAN), which integrates latent diffusion modelling with an attention-guided convolutional network. The diffusion model synthesizes realistic longitudinal neuroimaging trajectories from limited training data, enriching temporal context and improving robustness to unevenly spaced visits. The attention-convolutional layer then captures discriminative structural-temporal patterns that distinguish cognitively normal subjects from those with mild cognitive impairment and subjective cognitive decline. Experiments on the ADNI dataset demonstrate that DiGAN outperforms existing state-of-the-art baselines, showing its potential for early-stage AD detection.

---

### TruKAN: Towards More Efficient Kolmogorov-Arnold Networks Using Truncated Power Functions

Authors: Ali Bayeh, Samira Sadaoui, Malek Mouhoub
Published: 2026-02-02
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.03879v1

To address the trade-off between computational efficiency and adherence to Kolmogorov-Arnold Network (KAN) principles, we propose TruKAN, a new architecture based on the KAN structure and learnable activation functions. TruKAN replaces the B-spline basis in KAN with a family of truncated power functions derived from k-order spline theory. This change maintains the KAN's expressiveness while enhancing accuracy and training time. Each TruKAN layer combines a truncated power term with a polynomial term and employs either shared or individual knots. TruKAN exhibits greater interpretability than other KAN variants due to its simplified basis functions and knot configurations. By prioritizing interpretable basis functions, TruKAN aims to balance approximation efficacy with transparency. We develop the TruKAN model and integrate it into an advanced EfficientNet-V2-based framework, which is then evaluated on computer vision benchmark datasets. To ensure a fair comparison, we develop various models: MLP-, KAN-, SineKAN and TruKAN-based EfficientNet frameworks and assess their training time and accuracy across small and deep architectures. The training phase uses hybrid optimization to improve convergence stability. Additionally, we investigate layer normalization techniques for all the models and assess the impact of shared versus individual knots in TruKAN. Overall, TruKAN outperforms other KAN models in terms of accuracy, computational efficiency and memory usage on the complex vision task, demonstrating advantages beyond the limited settings explored in prior KAN studies.

---

### Intellectual Property Protection for 3D Gaussian Splatting Assets: A Survey

Authors: Longjie Zhao, Ziming Hong, Jiaxin Huang, Runnan Chen, Mingming Gong, Tongliang Liu
Published: 2026-02-02
Categories: cs.CV, cs.CR
arXiv: https://arxiv.org/abs/2602.03878v1

3D Gaussian Splatting (3DGS) has become a mainstream representation for real-time 3D scene synthesis, enabling applications in virtual and augmented reality, robotics, and 3D content creation. Its rising commercial value and explicit parametric structure raise emerging intellectual property (IP) protection concerns, prompting a surge of research on 3DGS IP protection. However, current progress remains fragmented, lacking a unified view of the underlying mechanisms, protection paradigms, and robustness challenges. To address this gap, we present the first systematic survey on 3DGS IP protection and introduce a bottom-up framework that examines (i) underlying Gaussian-based perturbation mechanisms, (ii) passive and active protection paradigms, and (iii) robustness threats under emerging generative AI era, revealing gaps in technical foundations and robustness characterization and indicating opportunities for deeper investigation. Finally, we outline six research directions across robustness, efficiency, and protection paradigms, offering a roadmap toward reliable and trustworthy IP protection for 3DGS assets.

---

### Training-Free Self-Correction for Multimodal Masked Diffusion Models

Authors: Yidong Ouyang, Panwen Hu, Zhengyan Wan, Zhe Wang, Liyan Xie, Dmitriy Bespalov, Ying Nian Wu, Guang Cheng, Hongyuan Zha, Qiang Sun
Published: 2026-02-02
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.02927v1

Masked diffusion models have emerged as a powerful framework for text and multimodal generation. However, their sampling procedure updates multiple tokens simultaneously and treats generated tokens as immutable, which may lead to error accumulation when early mistakes cannot be revised. In this work, we revisit existing self-correction methods and identify limitations stemming from additional training requirements or reliance on misaligned likelihood estimates. We propose a training-free self-correction framework that exploits the inductive biases of pre-trained masked diffusion models. Without modifying model parameters or introducing auxiliary evaluators, our method significantly improves generation quality on text-to-image generation and multimodal understanding tasks with reduced sampling steps. Moreover, the proposed framework generalizes across different masked diffusion architectures, highlighting its robustness and practical applicability. Code can be found in https://github.com/huge123/FreeCorrection.

---

### Refining Decision Boundaries In Anomaly Detection Using Similarity Search Within the Feature Space

Authors: Sidahmed Benabderrahmane, Petko Valtchev, James Cheney, Talal Rahwan
Published: 2026-02-02
Categories: cs.LG, cs.AI, cs.CR, cs.NE
arXiv: https://arxiv.org/abs/2602.02925v1

Detecting rare and diverse anomalies in highly imbalanced datasets-such as Advanced Persistent Threats (APTs) in cybersecurity-remains a fundamental challenge for machine learning systems. Active learning offers a promising direction by strategically querying an oracle to minimize labeling effort, yet conventional approaches often fail to exploit the intrinsic geometric structure of the feature space for model refinement. In this paper, we introduce SDA2E, a Sparse Dual Adversarial Attention-based AutoEncoder designed to learn compact and discriminative latent representations from imbalanced, high-dimensional data. We further propose a similarity-guided active learning framework that integrates three novel strategies to refine decision boundaries efficiently: mormal-like expansion, which enriches the training set with points similar to labeled normals to improve reconstruction fidelity; anomaly-like prioritization, which boosts ranking accuracy by focusing on points resembling known anomalies; and a hybrid strategy that combines both for balanced model refinement and ranking. A key component of our framework is a new similarity measure, Normalized Matching 1s (SIM_NM1), tailored for sparse binary embeddings. We evaluate SDA2E extensively across 52 imbalanced datasets, including multiple DARPA Transparent Computing scenarios, and benchmark it against 15 state-of-the-art anomaly detection methods. Results demonstrate that SDA2E consistently achieves superior ranking performance (nDCG up to 1.0 in several cases) while reducing the required labeled data by up to 80% compared to passive training. Statistical tests confirm the significance of these improvements. Our work establishes a robust, efficient, and statistically validated framework for anomaly detection that is particularly suited to cybersecurity applications such as APT detection.

---

### How Does the Lagrangian Guide Safe Reinforcement Learning through Diffusion Models?

Authors: Xiaoyuan Cheng, Wenxuan Yuan, Boyang Li, Yuanchao Xu, Yiming Yang, Hao Liang, Bei Peng, Robert Loftin, Zhuo Sun, Yukun Hu
Published: 2026-02-02
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2602.02924v2

Diffusion policy sampling enables reinforcement learning (RL) to represent multimodal action distributions beyond suboptimal unimodal Gaussian policies. However, existing diffusion-based RL methods primarily focus on offline settings for reward maximization, with limited consideration of safety in online settings. To address this gap, we propose Augmented Lagrangian-Guided Diffusion (ALGD), a novel algorithm for off-policy safe RL. By revisiting optimization theory and energy-based model, we show that the instability of primal-dual methods arises from the non-convex Lagrangian landscape. In diffusion-based safe RL, the Lagrangian can be interpreted as an energy function guiding the denoising dynamics. Counterintuitively, direct usage destabilizes both policy generation and training. ALGD resolves this issue by introducing an augmented Lagrangian that locally convexifies the energy landscape, yielding a stabilized policy generation and training process without altering the distribution of the optimal policy. Theoretical analysis and extensive experiments demonstrate that ALGD is both theoretically grounded and empirically effective, achieving strong and stable performance across diverse environments.

---

### A Reproducible Framework for Bias-Resistant Machine Learning on Small-Sample Neuroimaging Data

Authors: Jagan Mohan Reddy Dwarampudi, Jennifer L Purks, Joshua Wong, Renjie Hu, Tania Banerjee
Published: 2026-02-02
Categories: cs.LG, cs.CV, q-bio.NC, q-bio.QM
arXiv: https://arxiv.org/abs/2602.02920v1

We introduce a reproducible, bias-resistant machine learning framework that integrates domain-informed feature engineering, nested cross-validation, and calibrated decision-threshold optimization for small-sample neuroimaging data. Conventional cross-validation frameworks that reuse the same folds for both model selection and performance estimation yield optimistically biased results, limiting reproducibility and generalization. Demonstrated on a high-dimensional structural MRI dataset of deep brain stimulation cognitive outcomes, the framework achieved a nested-CV balanced accuracy of 0.660\,$\pm$\,0.068 using a compact, interpretable subset selected via importance-guided ranking. By combining interpretability and unbiased evaluation, this work provides a generalizable computational blueprint for reliable machine learning in data-limited biomedical domains.

---

### DeltaEvolve: Accelerating Scientific Discovery through Momentum-Driven Evolution

Authors: Jiachen Jiang, Tianyu Ding, Zhihui Zhu
Published: 2026-02-02
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.02919v1

LLM-driven evolutionary systems have shown promise for automated science discovery, yet existing approaches such as AlphaEvolve rely on full-code histories that are context-inefficient and potentially provide weak evolutionary guidance. In this work, we first formalize the evolutionary agents as a general Expectation-Maximization framework, where the language model samples candidate programs (E-step) and the system updates the control context based on evaluation feedback (M-step). Under this view, constructing context via full-code snapshots constitutes a suboptimal M-step, as redundant implement details dilutes core algorithmic ideas, making it difficult to provide clear inspirations for evolution. To address this, we propose DeltaEvolve, a momentum-driven evolutionary framework that replaces full-code history with structured semantic delta capturing how and why modifications between successive nodes affect performance. As programs are often decomposable, semantic delta usually contains many effective components which are transferable and more informative to drive improvement. By organizing semantic delta through multi-level database and progressive disclosure mechanism, input tokens are further reduced. Empirical evaluations on tasks across diverse scientific domains show that our framework can discover better solution with less token consumption over full-code-based evolutionary agents.

---

### A Multi-scale Linear-time Encoder for Whole-Slide Image Analysis

Authors: Jagan Mohan Reddy Dwarampudi, Joshua Wong, Hien Van Nguyen, Tania Banerjee
Published: 2026-02-02
Categories: cs.CV, cs.AI, cs.LG, q-bio.TO
arXiv: https://arxiv.org/abs/2602.02918v1

We introduce Multi-scale Adaptive Recurrent Biomedical Linear-time Encoder (MARBLE), the first \textit{purely Mamba-based} multi-state multiple instance learning (MIL) framework for whole-slide image (WSI) analysis. MARBLE processes multiple magnification levels in parallel and integrates coarse-to-fine reasoning within a linear-time state-space model, efficiently capturing cross-scale dependencies with minimal parameter overhead. WSI analysis remains challenging due to gigapixel resolutions and hierarchical magnifications, while existing MIL methods typically operate at a single scale and transformer-based approaches suffer from quadratic attention costs. By coupling parallel multi-scale processing with linear-time sequence modeling, MARBLE provides a scalable and modular alternative to attention-based architectures. Experiments on five public datasets show improvements of up to \textbf{6.9\%} in AUC, \textbf{20.3\%} in accuracy, and \textbf{2.3\%} in C-index, establishing MARBLE as an efficient and generalizable framework for multi-scale WSI analysis.

---

### Weighted Temporal Decay Loss for Learning Wearable PPG Data with Sparse Clinical Labels

Authors: Yunsung Chung, Keum San Chun, Migyeong Gwak, Han Feng, Yingshuo Liu, Chanho Lim, Viswam Nathan, Nassir Marrouche, Sharanya Arcot Desai
Published: 2026-02-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.02917v1

Advances in wearable computing and AI have increased interest in leveraging PPG for health monitoring over the past decade. One of the biggest challenges in developing health algorithms based on such biosignals is the sparsity of clinical labels, which makes biosignals temporally distant from lab draws less reliable for supervision. To address this problem, we introduce a simple training strategy that learns a biomarker-specific decay of sample weight over the time gap between a segment and its ground truth label and uses this weight in the loss with a regularizer to prevent trivial solutions. On smartwatch PPG from 450 participants across 10 biomarkers, the approach improves over baselines. In the subject-wise setting, the proposed approach averages 0.715 AUPRC, compared to 0.674 for a fine-tuned self-supervised baseline and 0.626 for a feature-based Random Forest. A comparison of four decay families shows that a simple linear decay function is most robust on average. Beyond accuracy, the learned decay rates summarize how quickly each biomarker's PPG evidence becomes stale, providing an interpretable view of temporal sensitivity.

---

### FaceLinkGen: A Re-evaluation of Identity Leakage in Privacy-Preserving Face Recognition and Face Anonymization Systems Using Simple Distillation

Authors: Wenqi Guo, Mohamed Shehata, Shan Du
Published: 2026-02-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.02914v3

Privacy-preserving face recognition (PPFR) hides facial appearance while retaining machine recognition, whereas perception-preserving face de-identification (De-ID) retains human recognizability while blocking face recognition models. We show that both designs preserve identity signals that an adaptive attacker can extract. We introduce FaceLinkGen, a unified distillation attack that learns from paired protected and original images. Across MinusFace, PartialFace, and DecoyFace, FaceLinkGen regenerates faces accepted by Face++ at rates of 81.0--99.0\% and by Amazon at rates of 74.9--99.2\%. Against four De-ID methods, it raises mixed-gallery Recall@1 to 55.2--89.6\% and remains effective with limited paired data. These results establish adaptive evaluation as essential for measuring facial privacy and show that resistance to fixed recognition or reconstruction models does not prevent identity leakage.

---

### FaceLinkGen: Rethinking Identity Leakage in Privacy-Preserving Face Recognition with Identity Extraction

Authors: Wenqi Guo, Shan Du
Published: 2026-02-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.02914v2

Transformation-based privacy-preserving face recognition (PPFR) aims to verify identities while hiding facial data from attackers and malicious service providers. Existing evaluations mostly treat privacy as resistance to pixel-level reconstruction, measured by PSNR and SSIM. We show that this reconstruction-centric view fails. We present FaceLinkGen, an identity extraction attack that performs linkage/matching and face regeneration directly from protected templates without recovering original pixels. On three recent PPFR systems, FaceLinkGen reaches over 98.5\% matching accuracy and above 96\% regeneration success, and still exceeds 92\% matching and 94\% regeneration in a near zero knowledge setting. These results expose a structural gap between pixel distortion metrics, which are widely used in PPFR evaluation, and real privacy. We show that visual obfuscation leaves identity information broadly exposed to both external intruders and untrusted service providers.

---

### Notes on the Reward Representation of Posterior Updates

Authors: Pedro A. Ortega
Published: 2026-02-02
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2602.02912v1

Many ideas in modern control and reinforcement learning treat decision-making as inference: start from a baseline distribution and update it when a signal arrives. We ask when this can be made literal rather than metaphorical. We study the special case where a KL-regularized soft update is exactly a Bayesian posterior inside a single fixed probabilistic model, so the update variable is a genuine channel through which information is transmitted. In this regime, behavioral change is driven only by evidence carried by that channel: the update must be explainable as an evidence reweighing of the baseline. This yields a sharp identification result: posterior updates determine the relative, context-dependent incentive signal that shifts behavior, but they do not uniquely determine absolute rewards, which remain ambiguous up to context-specific baselines. Requiring one reusable continuation value across different update directions adds a further coherence constraint linking the reward descriptions associated with different conditioning orders.

---

### Reasoning about Reasoning: BAPO Bounds on Chain-of-Thought Token Complexity in LLMs

Authors: Kiran Tomlinson, Tobias Schnabel, Adith Swaminathan, Jennifer Neville
Published: 2026-02-02
Categories: cs.AI, cs.FL, cs.LG
arXiv: https://arxiv.org/abs/2602.02909v2

Inference-time scaling via chain-of-thought (CoT) reasoning is a major driver of state-of-the-art LLM performance, but it comes with substantial latency and compute costs. We address a fundamental theoretical question: how many reasoning tokens are required to solve a problem as input size grows? By extending the bounded attention prefix oracle (BAPO) model--an abstraction of LLMs that quantifies the information flow required to solve a task--we prove lower bounds on the CoT tokens required for three canonical BAPO-hard tasks: binary majority, triplet matching, and graph reachability. We show that each requires $Ω(n)$ reasoning tokens when the input size is $n$. We complement these results with matching or near-matching upper bounds via explicit constructions. Finally, our experiments with frontier reasoning models show approximately linear reasoning token scaling on these tasks and failures when constrained to smaller reasoning budgets, consistent with our theoretical lower bounds. Together, our results identify fundamental bottlenecks in inference-time compute through CoT and offer a principled tool for analyzing optimal reasoning length.

---

### A Random Matrix Theory Perspective on the Consistency of Diffusion Models

Authors: Binxu Wang, Jacob Zavatone-Veth, Cengiz Pehlevan
Published: 2026-02-02
Categories: cs.LG, cs.AI, cs.CV, stat.ML
arXiv: https://arxiv.org/abs/2602.02908v2

Diffusion models trained on different, non-overlapping subsets of a dataset often produce strikingly similar outputs when given the same noise seed. We trace this consistency to a simple linear effect: the shared Gaussian statistics across splits already predict much of the generated images. To formalize this, we develop a random matrix theory (RMT) framework that quantifies how finite datasets shape the expectation and variance of the learned denoiser and sampling map in the linear setting. For expectations, sampling variability acts as a renormalization of the noise level through a self-consistent relation $σ^2 \mapsto κ(σ^2)$, explaining why limited data overshrink low-variance directions and pull samples toward the dataset mean. For fluctuations, our variance formulas reveal three key factors behind cross-split disagreement: \textit{anisotropy} across eigenmodes, \textit{inhomogeneity} across inputs, and overall scaling with dataset size. Extending deterministic-equivalence tools to fractional matrix powers further allows us to analyze entire sampling trajectories. The theory sharply predicts the behavior of linear diffusion models, and we validate its predictions on UNet and DiT architectures in their non-memorization regime, identifying where and how samples deviates across training data split. This provides a principled baseline for reproducibility in diffusion training, linking spectral properties of data to the stability of generative outputs.

---

### FIRE-Bench: Evaluating AI Agents on the Rediscovery of Scientific Insights

Authors: Zhen Wang, Fan Bai, Zhongyan Luo, Jinyan Su, Kaiser Sun, Xinle Yu, Jieyuan Liu, Kun Zhou, Claire Cardie, Mark Dredze, Zhiting Hu, Eric P. Xing
Published: 2026-02-02
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.02905v2

Autonomous agents powered by large language models (LLMs) promise to accelerate scientific discovery end-to-end, but rigorously evaluating their capacity for verifiable discovery remains a central challenge. Existing benchmarks face a trade-off: they either heavily rely on LLM-as-judge evaluations of automatically generated research outputs or optimize convenient yet isolated performance metrics that provide coarse proxies for scientific insight. To address this gap, we introduce FIRE-Bench (Full-cycle Insight Rediscovery Evaluation), a benchmark that evaluates agents through the rediscovery of established findings from recent, high-impact machine learning research. Agents are given only a high-level research question extracted from a published, verified study and must autonomously explore ideas, design experiments, implement code, execute their plans, and derive conclusions supported by empirical evidence. We evaluate a range of state-of-the-art agents with frontier LLMs backbones like gpt-5 on FIRE-Bench. Our results show that full-cycle scientific research remains challenging for current agent systems: even the strongest agents achieve limited rediscovery success (<50 F1), exhibit high variance across runs, and display recurring failure modes in experimental design, execution, and evidence-based reasoning. FIRE-Bench provides a rigorous and diagnostic framework for measuring progress toward reliable agent-driven scientific discovery.

---

### Spatiotemporal Decision Transformer for Traffic Coordination

Authors: Haoran Su, Yandong Sun, Hanxiao Deng
Published: 2026-02-02
Categories: cs.LG, cs.AI, eess.SY
arXiv: https://arxiv.org/abs/2602.02903v1

Traffic signal control is a critical challenge in urban transportation, requiring coordination among multiple intersections to optimize network-wide traffic flow. While reinforcement learning has shown promise for adaptive signal control, existing methods struggle with multi-agent coordination and sample efficiency. We introduce MADT (Multi-Agent Decision Transformer), a novel approach that reformulates multi-agent traffic signal control as a sequence modeling problem. MADT extends the Decision Transformer paradigm to multi-agent settings by incorporating: (1) a graph attention mechanism for modeling spatial dependencies between intersections, (2) a|temporal transformer encoder for capturing traffic dynamics, and (3) return-to-go conditioning for target performance specification. Our approach enables offline learning from historical traffic data, with architecture design that facilitates potential online fine-tuning. Experiments on synthetic grid networks and real-world traffic scenarios demonstrate that MADT achieves state-of-the-art performance, reducing average travel time by 5-6% compared to the strongest baseline while exhibiting superior coordination among adjacent intersections.

---

### Minimal Computational Preconditions for Subjective Perspective in Artificial Agents

Authors: Hongju Pae
Published: 2026-02-02
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.02902v2

This study operationalizes subjective perspective in artificial agents by grounding it in a minimal, phenomenologically motivated internal structure. The perspective is implemented as a slowly evolving global latent state that modulates fast policy dynamics without being directly optimized for behavioral consequences. In a reward-free environment with regime shifts, this latent structure exhibits direction-dependent hysteresis, while policy-level behavior remains comparatively reactive. I argue that such hysteresis constitutes a measurable signature of perspective-like subjectivity in machine systems.

---

### Manifold-Constrained Energy-Based Transition Models for Offline Reinforcement Learning

Authors: Zeyu Fang, Zuyuan Zhang, Mahdi Imani, Tian Lan
Published: 2026-02-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.02900v1

Model-based offline reinforcement learning is brittle under distribution shift: policy improvement drives rollouts into state--action regions weakly supported by the dataset, where compounding model error yields severe value overestimation. We propose Manifold-Constrained Energy-based Transition Models (MC-ETM), which train conditional energy-based transition models using a manifold projection--diffusion negative sampler. MC-ETM learns a latent manifold of next states and generates near-manifold hard negatives by perturbing latent codes and running Langevin dynamics in latent space with the learned conditional energy, sharpening the energy landscape around the dataset support and improving sensitivity to subtle out-of-distribution deviations. For policy optimization, the learned energy provides a single reliability signal: rollouts are truncated when the minimum energy over sampled next states exceeds a threshold, and Bellman backups are stabilized via pessimistic penalties based on Q-value-level dispersion across energy-guided samples. We formalize MC-ETM through a hybrid pessimistic MDP formulation and derive a conservative performance bound separating in-support evaluation error from truncation risk. Empirically, MC-ETM improves multi-step dynamics fidelity and yields higher normalized returns on standard offline control benchmarks, particularly under irregular dynamics and sparse data coverage.

---

### Decentralized SGD with Controlled Disagreement Finds Flatter Minima

Authors: Zesen Wang, Mikael Johansson
Published: 2026-02-02
Categories: cs.LG, cs.DC
arXiv: https://arxiv.org/abs/2602.02899v2

Decentralized training is often regarded as inferior to centralized training because the consensus errors between workers are thought to undermine convergence and generalization. This work challenges this view by introducing decentralized SGD with Adaptive Consensus (DSGD-AC), which uses a time-dependent scaling mechanism to maintain consensus errors throughout the training. We show that adaptive consensus changes the stationary variance of disagreement modes by balancing two effects: it preserves consensus-error magnitude through weaker graph damping while still allowing curvature-dependent damping to shape the disagreement directions. This balance can produce a stronger Hessian-weighted loss-envelope penalty around the deployed model, even when normalized Hessian alignment is weaker than in standard DSGD. Empirical results on image classification show that DSGD-AC reaches flatter solutions and higher test accuracy than standard DSGD and even centralized SGD. Together, these results support consensus errors as a useful implicit regularizer and open a new perspective on the design of decentralized learning algorithms.

---

### Aligning Language Model Benchmarks with Pairwise Preferences

Authors: Marco Gutierrez, Xinyi Leng, Hannah Cyberey, Jonathan Richard Schwarz, Ahmed Alaa, Thomas Hartvigsen
Published: 2026-02-02
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.02898v4

Language model benchmarks are pervasive and computationally-efficient proxies for real-world performance. However, many recent works find that benchmarks often fail to predict real utility. Towards bridging this gap, we introduce benchmark alignment, where we use limited amounts of information about model performance to automatically update offline benchmarks, aiming to produce new static benchmarks that predict model pairwise preferences in given test settings. We then propose BenchAlign, the first solution to this problem, which learns preference-aligned weightings for benchmark questions using the question-level performance of language models alongside ranked pairs of models that could be collected during deployment, producing new benchmarks that rank previously unseen models according to these preferences. Our experiments show that our aligned benchmarks can accurately rank unseen models according to models of human preferences, even across different sizes, while remaining interpretable. Overall, our work provides insights into the limits of aligning benchmarks with practical human preferences, which stands to accelerate model development towards real utility.

---