# Research Papers — 2026-02 · bundle page 10 of 210

> Full-text markdown of papers #451–500 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/10
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/9.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/11.md)

### Task Complexity Matters: An Empirical Study of Reasoning in LLMs for Sentiment Analysis

Authors: Donghao Huang, Zhaoxia Wang
Published: 2026-02-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.24060v1

Large language models (LLMs) with reasoning capabilities have fueled a compelling narrative that reasoning universally improves performance across language tasks. We test this claim through a comprehensive evaluation of 504 configurations across seven model families--including adaptive, conditional, and reinforcement learning-based reasoning architectures--on sentiment analysis datasets of varying granularity (binary, five-class, and 27-class emotion). Our findings reveal that reasoning effectiveness is strongly task-dependent, challenging prevailing assumptions: (1) Reasoning shows task-complexity dependence--binary classification degrades up to -19.9 F1 percentage points (pp), while 27-class emotion recognition gains up to +16.0pp; (2) Distilled reasoning variants underperform base models by 3-18 pp on simpler tasks, though few-shot prompting enables partial recovery; (3) Few-shot learning improves over zero-shot in most cases regardless of model type, with gains varying by architecture and task complexity; (4) Pareto frontier analysis shows base models dominate efficiency-performance trade-offs, with reasoning justified only for complex emotion recognition despite 2.1x-54x computational overhead. We complement these quantitative findings with qualitative error analysis revealing that reasoning degrades simpler tasks through systematic over-deliberation, offering mechanistic insight beyond the high-level overthinking hypothesis.

---

### Quant Experts: Token-aware Adaptive Error Reconstruction with Mixture of Experts for Large Vision-Language Models Quantization

Authors: Chenwei Jia, Baoting Li, Xuchong Zhang, Mingzhuo Wei, Bochen Lin, Hongbin Sun
Published: 2026-02-27
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.24059v1

Post-Training Quantization (PTQ) has emerged as an effective technique for alleviating the substantial computational and memory overheads of Vision-Language Models (VLMs) by compressing both weights and activations without retraining the full model. Existing PTQ methods primarily rely on static identification and global compensation of sensitive or outlier channels, yet they often overlook the distributional differences of these important channels across inputs, leading to unsatisfactory quantization. In this work, we observe that the distributions and occurrence frequencies of important channels vary significantly both across modalities and among tokens, even within the same modality. Accordingly, we propose \textbf{Quant Experts (QE)}, a token-aware adaptive error compensation with mixture-of-experts for VLMs quantization. QE divides the important channels into token-independent and token-dependent groups. For the former, a shared expert is designed for most tokens to compensate for global quantization error using a low-rank adapter. For the latter, routed experts including multiple routed low-rank adapters are elaborated to compensate for local quantization error related to specific tokens. Extensive experiments demonstrate that QE consistently enhances task accuracy across various quantization settings and model scales, ranging from 2B to 70B parameters, while maintaining performance comparable to full-precision models.

---

### CIRCLE: A Framework for Evaluating AI from a Real-World Lens

Authors: Reva Schwartz, Carina Westling, Morgan Briggs, Marzieh Fadaee, Isar Nejadgholi, Matthew Holmes, Fariza Rashid, Maya Carlyle, Afaf Taïk, Kyra Wilson, Peter Douglas, Theodora Skeadas et al.
Published: 2026-02-27
Categories: cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2602.24055v5

This study proposes CIRCLE, a six-stage, lifecycle-based framework to bridge the reality gap between model-centric performance metrics and AI system outcomes in deployment. Current approaches such as MLOps frameworks and AI model benchmarks offer detailed insights into system stability and model capabilities, but they do not provide decision makers outside the AI stack with systematic evidence of how these systems actually behave in real world contexts or affect their organizations over time. CIRCLE operationalizes the Validation phase of TEVV (Test, Evaluation, Verification, and Validation) by translating priorities of stakeholders outside the stack into measurable signals. Unlike participatory design which often remains localized, or algorithmic audits which are often retrospective, CIRCLE provides a structured, prospective protocol for linking context sensitive qualitative insights to scalable quantitative metrics. By integrating methods such as field testing, red teaming, and longitudinal studies into a coordinated pipeline, CIRCLE produces systematic knowledge; evidence that is comparable across sites yet sensitive to local context. This can enable governance based on materialized downstream effects rather than theoretical capabilities.

---

### CIRCLE: A Framework for Evaluating AI from a Real-World Lens

Authors: Reva Schwartz, Carina Westling, Morgan Briggs, Marzieh Fadaee, Isar Nejadgholi, Matthew Holmes, Fariza Rashid, Maya Carlyle, Afaf Taïk, Kyra Wilson, Peter Douglas, Theodora Skeadas et al.
Published: 2026-02-27
Categories: cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2602.24055v4

This paper proposes CIRCLE, a six-stage, lifecycle-based framework to bridge the reality gap between model-centric performance metrics and AI's materialized outcomes in deployment. Current approaches such as MLOps frameworks and AI model benchmarks offer detailed insights into system stability and model capabilities, but they do not provide decision-makers outside the AI stack with systematic evidence of how these systems actually behave in real-world contexts or affect their organizations over time. CIRCLE operationalizes the Validation phase of TEVV (Test, Evaluation, Verification, and Validation) by formalizing the translation of stakeholder concerns outside the stack into measurable signals. Unlike participatory design, which often remains localized, or algorithmic audits, which are often retrospective, CIRCLE provides a structured, prospective protocol for linking context-sensitive qualitative insights to scalable quantitative metrics. By integrating methods such as field testing, red teaming, and longitudinal studies into a coordinated pipeline, CIRCLE produces systematic knowledge: evidence that is comparable across sites yet sensitive to local context. This, in turn, can enable governance based on materialized downstream effects rather than theoretical capabilities.

---

### Unsupervised Baseline Clustering and Incremental Adaptation for IoT Device Traffic Profiling

Authors: Sean M. Alderman, John D. Hastings
Published: 2026-02-27
Categories: cs.NI, cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2602.24047v1

The growth and heterogeneity of IoT devices create security challenges where static identification models can degrade as traffic evolves. This paper presents a two-stage, flow-feature-based pipeline for unsupervised IoT device traffic profiling and incremental model updating, evaluated on selected long-duration captures from the Deakin IoT dataset. For baseline profiling, density-based clustering (DBSCAN) isolates a substantial outlier portion of the data and produces the strongest alignment with ground-truth device labels among tested classical methods (NMI 0.78), outperforming centroid-based clustering on cluster purity. For incremental adaptation, we evaluate stream-oriented clustering approaches and find that BIRCH supports efficient updates (0.13 seconds per update) and forms comparatively coherent clusters for a held-out novel device (purity 0.87), but with limited capture of novel traffic (share 0.72) and a measurable trade-off in known-device accuracy after adaptation (0.71). Overall, the results highlight a practical trade-off between high-purity static profiling and the flexibility of incremental clustering for evolving IoT environments.

---

### Data Driven Optimization of GPU efficiency for Distributed LLM-Adapter Serving

Authors: Ferran Agullo, Joan Oliveras, Chen Wang, Alberto Gutierrez-Torre, Olivier Tardieu, Alaa Youssef, Jordi Torres, Josep Ll. Berral
Published: 2026-02-27
Categories: cs.DC, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.24044v2

Large Language Model (LLM) adapters enable low-cost model specialization, but introduce complex caching and scheduling challenges in distributed serving systems where hundreds of adapters must be hosted concurrently. While prior work has largely focused on latency and throughput optimization, minimizing GPU resource requirements through near-peak utilization remains largely underexplored. This paper presents a data-driven pipeline that, for a given workload, computes an adapter placement that serves the workload with the minimum number of GPUs while avoiding request starvation and GPU memory errors. To that end, the approach identifies the maximum feasible throughput attainable on each GPU by leveraging accurate performance predictions learned from real serving behavior. The proposed pipeline integrates three components: (i) a Digital Twin (DT) tailored to LLM-adapter serving, (ii) a distilled machine learning (ML) model trained on DT-generated data, and (iii) a greedy placement algorithm that exploits ML-based performance estimates to maximize GPU efficiency. The DT emulates real system dynamics with high fidelity, achieving below 5% throughput estimation error while executing up to 90x faster than full LLM benchmarking across both predictable and unpredictable workloads. The learned ML models further accelerate performance estimation with marginal accuracy degradation, enabling scalable optimization. Experimental results demonstrate that the pipeline substantially improves GPU efficiency, reducing the number of GPUs required to sustain target workloads by 60\% on average across the evaluated scenarios. Beyond GPU efficiency, the pipeline can be adapted to alternative objectives, such as latency minimization, highlighting its versatility for future large-scale LLM serving infrastructures.

---

### Spatio-Temporal Garment Reconstruction Using Diffusion Mapping via Pattern Coordinates

Authors: Yingxuan You, Ren Li, Corentin Dumery, Cong Cao, Hao Li, Pascal Fua
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.24043v2

Reconstructing 3D clothed humans from monocular images and videos is a fundamental problem with applications in virtual try-on, avatar creation, and mixed reality. Despite significant progress in human body recovery, accurately reconstructing garment geometry, particularly for loose-fitting clothing, remains an open challenge. We propose a unified framework for high-fidelity 3D garment reconstruction from both single images and video sequences. Our approach combines Implicit Sewing Patterns (ISP) with a generative diffusion model to learn expressive garment shape priors in 2D UV space. Leveraging these priors, we introduce a mapping model that establishes correspondences between image pixels, UV pattern coordinates, and 3D geometry, enabling accurate and detailed garment reconstruction from single images. We further extend this formulation to dynamic reconstruction by introducing a spatio-temporal diffusion scheme with test-time guidance to enforce long-range temporal consistency. We also develop analytic projection-based constraints that preserve image-aligned geometry in visible regions while enforcing coherent completion in occluded areas over time. Although trained exclusively on synthetically simulated cloth data, our method generalizes well to real-world imagery and consistently outperforms existing approaches on both tight- and loose-fitting garments. The reconstructed garments preserve fine geometric detail while exhibiting realistic dynamic motion, supporting downstream applications such as texture editing, garment retargeting, and animation.

---

### Spatio-Temporal Garment Reconstruction Using Diffusion Mapping via Pattern Coordinates

Authors: Yingxuan You, Ren Li, Corentin Dumery, Cong Cao, Hao Li, Pascal Fua
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.24043v1

Reconstructing 3D clothed humans from monocular images and videos is a fundamental problem with applications in virtual try-on, avatar creation, and mixed reality. Despite significant progress in human body recovery, accurately reconstructing garment geometry, particularly for loose-fitting clothing, remains an open challenge. We propose a unified framework for high-fidelity 3D garment reconstruction from both single images and video sequences. Our approach combines Implicit Sewing Patterns (ISP) with a generative diffusion model to learn expressive garment shape priors in 2D UV space. Leveraging these priors, we introduce a mapping model that establishes correspondences between image pixels, UV pattern coordinates, and 3D geometry, enabling accurate and detailed garment reconstruction from single images. We further extend this formulation to dynamic reconstruction by introducing a spatio-temporal diffusion scheme with test-time guidance to enforce long-range temporal consistency. We also develop analytic projection-based constraints that preserve image-aligned geometry in visible regions while enforcing coherent completion in occluded areas over time. Although trained exclusively on synthetically simulated cloth data, our method generalizes well to real-world imagery and consistently outperforms existing approaches on both tight- and loose-fitting garments. The reconstructed garments preserve fine geometric detail while exhibiting realistic dynamic motion, supporting downstream applications such as texture editing, garment retargeting, and animation.

---

### Look Carefully: Adaptive Visual Reinforcements in Multimodal Large Language Models for Hallucination Mitigation

Authors: Xingyu Zhu, Kesen Zhao, Liang Yi, Shuo Wang, Zhicai Wang, Beier Zhu, Hanwang Zhang
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.24041v1

Multimodal large language models (MLLMs) have achieved remarkable progress in vision-language reasoning, yet they remain vulnerable to hallucination, where generated content deviates from visual evidence. Existing mitigation strategies either require costly supervision during training or introduce additional latency at inference time. Recent vision enhancement methods attempt to address this issue by reinforcing visual tokens during decoding, but they typically inject all tokens indiscriminately, which causes interference from background regions and distracts the model from critical cues. To overcome this challenge, we propose Adaptive Visual Reinforcement (AIR), a training-free framework for MLLMs. AIR consists of two components. Prototype-based token reduction condenses the large pool of visual tokens into a compact subset to suppress redundancy. OT-guided patch reinforcement quantifies the alignment between hidden states and patch embeddings to selectively integrate the most consistent patches into feed-forward layers. As a result, AIR enhances the model's reliance on salient visual information and effectively mitigates hallucination. Extensive experiments across representative MLLMs demonstrate that AIR substantially reduces hallucination while preserving general capabilities, establishing it as an effective solution for building reliable MLLMs.

---

### RewardUQ: A Unified Framework for Uncertainty-Aware Reward Models

Authors: Daniel Yang, Samuel Stante, Florian Redhardt, Lena Libon, Parnian Kassraie, Ido Hakimi, Barna Pásztor, Andreas Krause
Published: 2026-02-27
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.24040v1

Reward models are central to aligning large language models (LLMs) with human preferences. Yet most approaches rely on pointwise reward estimates that overlook the epistemic uncertainty in reward models arising from limited human feedback. Recent work suggests that quantifying this uncertainty can reduce the costs of human annotation via uncertainty-guided active learning and mitigate reward overoptimization in LLM post-training. However, uncertainty-aware reward models have so far been adopted without thorough comparison, leaving them poorly understood. This work introduces a unified framework, RewardUQ, to systematically evaluate uncertainty quantification for reward models. We compare common methods along standard metrics measuring accuracy and calibration, and we propose a new ranking strategy incorporating both dimensions for a simplified comparison. Our experimental results suggest that model size and initialization have the most meaningful impact on performance, and most prior work could have benefited from alternative design choices. To foster the development and evaluation of new methods and aid the deployment in downstream applications, we release our open-source framework as a Python package. Our code is available at https://github.com/lasgroup/rewarduq.

---

### Portfolio Reinforcement Learning with Scenario-Context Rollout

Authors: Vanya Priscillia Bendatu, Yao Lu
Published: 2026-02-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.24037v1

Market regime shifts induce distribution shifts that can degrade the performance of portfolio rebalancing policies. We propose macro-conditioned scenario-context rollout (SCR) that generates plausible next-day multivariate return scenarios under stress events. However, doing so faces new challenges, as history will never tell what would have happened differently. As a result, incorporating scenario-based rewards from rollouts introduces a reward--transition mismatch in temporal-difference learning, destabilizing RL critic training. We analyze this inconsistency and show it leads to a mixed evaluation target. Guided by this analysis, we construct a counterfactual next state using the rollout-implied continuations and augment the critic agent's bootstrap target. Doing so stabilizes the learning and provides a viable bias-variance tradeoff. In out-of-sample evaluations across 31 distinct universes of U.S. equity and ETF portfolios, our method improves Sharpe ratio by up to 76% and reduces maximum drawdown by up to 53% compared with classic and RL-based portfolio rebalancing baselines.

---

### GuardAlign: Test-time Safety Alignment in Multimodal Large Language Models

Authors: Xingyu Zhu, Beier Zhu, Junfeng Fang, Shuo Wang, Yin Zhang, Xiang Wang, Xiangnan He
Published: 2026-02-27
Categories: cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2602.24027v1

Large vision-language models (LVLMs) have achieved remarkable progress in vision-language reasoning tasks, yet ensuring their safety remains a critical challenge. Recent input-side defenses detect unsafe images with CLIP and prepend safety prefixes to prompts, but they still suffer from inaccurate detection in complex scenes and unstable safety signals during decoding. To address these issues, we propose GuardAlign, a training-free defense framework that integrates two strategies. First, OT-enhanced safety detection leverages optimal transport to measure distribution distances between image patches and unsafe semantics, enabling accurate identification of malicious regions without additional computational cost. Second, cross-modal attentive calibration strengthens the influence of safety prefixes by adaptively reallocating attention across layers, ensuring that safety signals remain consistently activated throughout generation. Extensive evaluations on six representative MLLMs demonstrate that GuardAlign reduces unsafe response rates by up to 39% on SPA-VL, while preserving utility, achieving an improvement on VQAv2 from 78.51% to 79.21%.

---

### Steering and Rectifying Latent Representation Manifolds in Frozen Multi-modal LLMs for Video Anomaly Detection

Authors: Zhaolin Cai, Fan Li, Huiyu Duan, Lijun He, Guangtao Zhai
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.24021v1

Video anomaly detection (VAD) aims to identify abnormal events in videos. Traditional VAD methods generally suffer from the high costs of labeled data and full training, thus some recent works have explored leveraging frozen multi-modal large language models (MLLMs) in a tuning-free manner to perform VAD. However, their performance is limited as they directly inherit pre-training biases and cannot adapt internal representations to specific video contexts, leading to difficulties in handling subtle or ambiguous anomalies. To address these limitations, we propose a novel intervention framework, termed SteerVAD, which advances MLLM-based VAD by shifting from passively reading to actively steering and rectifying internal representations. Our approach first leverages the gradient-free representational separability analysis (RSA) to identify top attention heads as latent anomaly experts (LAEs) which are most discriminative for VAD. Then a hierarchical meta-controller (HMC) generates dynamic rectification signals by jointly conditioning on global context and these LAE outputs. The signals execute targeted, anisotropic scaling directly upon the LAE representation manifolds, amplifying anomaly-relevant dimensions while suppressing inherent biases. Extensive experiments on mainstream benchmarks demonstrate our method achieves state-of-the-art performance among tuning-free approaches requiring only 1% of training data, establishing it as a powerful new direction for video anomaly detection. The code will be released upon the publication.

---

### SR3R: Rethinking Super-Resolution 3D Reconstruction With Feed-Forward Gaussian Splatting

Authors: Xiang Feng, Xiangbo Wang, Tieshi Zhong, Chengkai Wang, Yiting Zhao, Tianxiang Xu, Zhenzhong Kuang, Feiwei Qin, Xuefei Yin, Yanming Zhu
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.24020v1

3D super-resolution (3DSR) aims to reconstruct high-resolution (HR) 3D scenes from low-resolution (LR) multi-view images. Existing methods rely on dense LR inputs and per-scene optimization, which restricts the high-frequency priors for constructing HR 3D Gaussian Splatting (3DGS) to those inherited from pretrained 2D super-resolution (2DSR) models. This severely limits reconstruction fidelity, cross-scene generalization, and real-time usability. We propose to reformulate 3DSR as a direct feed-forward mapping from sparse LR views to HR 3DGS representations, enabling the model to autonomously learn 3D-specific high-frequency geometry and appearance from large-scale, multi-scene data. This fundamentally changes how 3DSR acquires high-frequency knowledge and enables robust generalization to unseen scenes. Specifically, we introduce SR3R, a feed-forward framework that directly predicts HR 3DGS representations from sparse LR views via the learned mapping network. To further enhance reconstruction fidelity, we introduce Gaussian offset learning and feature refinement, which stabilize reconstruction and sharpen high-frequency details. SR3R is plug-and-play and can be paired with any feed-forward 3DGS reconstruction backbone: the backbone provides an LR 3DGS scaffold, and SR3R upscales it to an HR 3DGS. Extensive experiments across three 3D benchmarks demonstrate that SR3R surpasses state-of-the-art (SOTA) 3DSR methods and achieves strong zero-shot generalization, even outperforming SOTA per-scene optimization methods on unseen scenes.

---

### Interpretable Debiasing of Vision-Language Models for Social Fairness

Authors: Na Min An, Yoonna Jang, Yusuke Hirota, Ryo Hachiuma, Isabelle Augenstein, Hyunjung Shim
Published: 2026-02-27
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.24014v1

The rapid advancement of Vision-Language models (VLMs) has raised growing concerns that their black-box reasoning processes could lead to unintended forms of social bias. Current debiasing approaches focus on mitigating surface-level bias signals through post-hoc learning or test-time algorithms, while leaving the internal dynamics of the model largely unexplored. In this work, we introduce an interpretable, model-agnostic bias mitigation framework, DeBiasLens, that localizes social attribute neurons in VLMs through sparse autoencoders (SAEs) applied to multimodal encoders. Building upon the disentanglement ability of SAEs, we train them on facial image or caption datasets without corresponding social attribute labels to uncover neurons highly responsive to specific demographics, including those that are underrepresented. By selectively deactivating the social neurons most strongly tied to bias for each group, we effectively mitigate socially biased behaviors of VLMs without degrading their semantic knowledge. Our research lays the groundwork for future auditing tools, prioritizing social fairness in emerging real-world AI systems.

---

### Ordinal Diffusion Models for Color Fundus Images

Authors: Gustav Schmidt, Philipp Berens, Sarah Müller
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.24013v2

Generative image models such as diffusion models can improve performance on clinically relevant tasks by offering deep learning models supplementary training data. However, most conditional diffusion models treat disease stages as independent classes, ignoring the continuous nature of disease progression. This mismatch is problematic in medical imaging because continuous pathological processes are typically only observed through coarse, discrete but ordered labels as in ophthalmology for diabetic retinopathy (DR). We propose an ordinal latent diffusion model for generating color fundus images that explicitly incorporates the ordered structure of DR severity into the generation process. Instead of categorical conditioning, we used a scalar disease representation, enabling a smooth transition between adjacent stages. We evaluated our approach using visual realism metrics and classification-based clinical consistency analysis on the EyePACS dataset. Compared to a standard conditional diffusion model, our model reduced the Fréchet inception distance for four of the five DR stages and increased the quadratic weighted $κ$ from 0.79 to 0.87. Furthermore, interpolation experiments showed that the model captured a continuous spectrum of disease progression learned from ordered, coarse class labels. Code available at https://github.com/berenslab/OrdinalDiffusionModels.

---

### Ordinal Diffusion Models for Color Fundus Images

Authors: Gustav Schmidt, Philipp Berens, Sarah Müller
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.24013v1

It has been suggested that generative image models such as diffusion models can improve performance on clinically relevant tasks by offering deep learning models supplementary training data. However, most conditional diffusion models treat disease stages as independent classes, ignoring the continuous nature of disease progression. This mismatch is problematic in medical imaging because continuous pathological processes are typically only observed through coarse, discrete but ordered labels as in ophthalmology for diabetic retinopathy (DR). We propose an ordinal latent diffusion model for generating color fundus images that explicitly incorporates the ordered structure of DR severity into the generation process. Instead of categorical conditioning, we used a scalar disease representation, enabling a smooth transition between adjacent stages. We evaluated our approach using visual realism metrics and classification-based clinical consistency analysis on the EyePACS dataset. Compared to a standard conditional diffusion model, our model reduced the Fréchet inception distance for four of the five DR stages and increased the quadratic weighted $κ$ from 0.79 to 0.87. Furthermore, interpolation experiments showed that the model captured a continuous spectrum of disease progression learned from ordered, coarse class labels.

---

### InfoNCE Induces Gaussian Distribution

Authors: Roy Betser, Eyal Gofer, Meir Yossef Levi, Guy Gilboa
Published: 2026-02-27
Categories: cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2602.24012v2

Contrastive learning has become a cornerstone of modern representation learning, allowing training with massive unlabeled data for both task-specific and general (foundation) models. A prototypical loss in contrastive training is InfoNCE and its variants. In this work, we show that the InfoNCE objective induces Gaussian structure in representations that emerge from contrastive training. We establish this result in two complementary regimes. First, we show that under certain alignment and concentration assumptions, projections of the high-dimensional representation asymptotically approach a multivariate Gaussian distribution. Next, under less strict assumptions, we show that adding a small asymptotically vanishing regularization term that promotes low feature norm and high feature entropy leads to similar asymptotic results. We support our analysis with experiments on synthetic and CIFAR-10 datasets across multiple encoder architectures and sizes, demonstrating consistent Gaussian behavior. This perspective provides a principled explanation for commonly observed Gaussianity in contrastive representations. The resulting Gaussian model enables principled analytical treatment of learned representations and is expected to support a wide range of applications in contrastive learning.

---

### Jailbreak Foundry: From Papers to Runnable Attacks for Reproducible Benchmarking

Authors: Zhicheng Fang, Jingjie Zheng, Chenxu Fu, Wei Xu
Published: 2026-02-27
Categories: cs.CR, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.24009v4

Jailbreak techniques for large language models (LLMs) evolve faster than benchmarks, making robustness estimates stale and difficult to compare across papers due to drift in datasets, harnesses, and judging protocols. We introduce JAILBREAK FOUNDRY (JBF), a system that addresses this gap via a multi-agent workflow to translate jailbreak papers into executable modules for immediate evaluation within a unified harness. JBF features three core components: (i) JBF-LIB for shared contracts and reusable utilities; (ii) JBF-FORGE for the multi-agent paper-to-module translation; and (iii) JBF-EVAL for standardizing evaluations. Across 30 reproduced attacks, JBF achieves high fidelity with a mean (reproduced-reported) attack success rate (ASR) deviation of +0.26 percentage points. By leveraging shared infrastructure, JBF reduces attack-specific implementation code by more than half relative to original repositories and achieves an 82.5% mean reused-code ratio. This system enables a standardized AdvBench evaluation of all 30 attacks across 10 victim models using a consistent GPT-4o judge. By automating both attack integration and standardized evaluation, JBF offers a scalable solution for creating living benchmarks that keep pace with the rapidly shifting security landscape.

---

### Inference-time optimization for experiment-grounded protein ensemble generation

Authors: Advaith Maddipatla, Anar Rzayev, Marco Pegoraro, Martin Pacesa, Paul Schanda, Ailie Marx, Sanketh Vedula, Alex M. Bronstein
Published: 2026-02-27
Categories: q-bio.BM, cs.LG
arXiv: https://arxiv.org/abs/2602.24007v3

Protein function relies on dynamic conformational ensembles, yet current generative models like AlphaFold3 often fail to produce ensembles that match experimental data. Recent experiment-guided generators attempt to address this by steering the reverse diffusion process. However, these methods are limited by fixed sampling horizons and sensitivity to initialization, often yielding thermodynamically implausible results. We introduce a general inference-time optimization framework to solve these challenges. First, we optimize over latent representations to maximize ensemble log-likelihood, rather than perturbing structures post hoc. This approach eliminates dependence on diffusion length, removes initialization bias, and easily incorporates external constraints. Second, we present novel sampling schemes for drawing Boltzmann-weighted ensembles. By combining structural priors from AlphaFold3 with force-field-based priors, we sample from their product distribution while balancing experimental likelihoods. Our results show that this framework consistently outperforms state-of-the-art guidance, improving diversity, physical energy, and agreement with data in X-ray crystallography and NMR, often fitting the experimental data better than deposited PDB structures. Finally, inference-time optimization experiments maximizing ipTM scores reveal that perturbing AlphaFold3 embeddings can artificially inflate model confidence. This exposes a vulnerability in current design metrics, whose mitigation could offer a pathway to reduce false discovery rates in binder engineering.

---

### Dialect and Gender Bias in YouTube's Spanish Captioning System

Authors: Iris Dania Jimenez, Christoph Kern
Published: 2026-02-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.24002v1

Spanish is the official language of twenty-one countries and is spoken by over 441 million people. Naturally, there are many variations in how Spanish is spoken across these countries. Media platforms such as YouTube rely on automatic speech recognition systems to make their content accessible to different groups of users. However, YouTube offers only one option for automatically generating captions in Spanish. This raises the question: could this captioning system be biased against certain Spanish dialects? This study examines the potential biases in YouTube's automatic captioning system by analyzing its performance across various Spanish dialects. By comparing the quality of captions for female and male speakers from different regions, we identify systematic disparities which can be attributed to specific dialects. Our study provides further evidence that algorithmic technologies deployed on digital platforms need to be calibrated to the diverse needs and experiences of their user populations.

---

### Foundation World Models for Agents that Learn, Verify, and Adapt Reliably Beyond Static Environments

Authors: Florent Delgrange
Published: 2026-02-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.23997v1

The next generation of autonomous agents must not only learn efficiently but also act reliably and adapt their behavior in open worlds. Standard approaches typically assume fixed tasks and environments with little or no novelty, which limits world models' ability to support agents that must evolve their policies as conditions change. This paper outlines a vision for foundation world models: persistent, compositional representations that unify reinforcement learning, reactive/program synthesis, and abstraction mechanisms. We propose an agenda built around four components: (i) learnable reward models from specifications to support optimization with clear objectives; (ii) adaptive formal verification integrated throughout learning; (iii) online abstraction calibration to quantify the reliability of the model's predictions; and (iv) test-time synthesis and world-model generation guided by verifiers. Together, these components enable agents to synthesize verifiable programs, derive new policies from a small number of interactions, and maintain correctness while adapting to novelty. The resulting framework positions foundation world models as a substrate for learning, reasoning, and adaptation, laying the groundwork for agents that not only act well but can explain and justify the behavior they adopt.

---

### Accelerating Masked Image Generation by Learning Controlled Latent Dynamics

Authors: Kaiwen Zhu, Quansheng Zeng, Yuandong Pu, Shuo Cao, Xiaohui Li, Yi Xin, Qi Qin, Jiayang Li, Juncheng Yan, Yu Qiao, Jinjin Gu, Yihao Liu
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.23996v2

Masked Image Generation Models (MIGMs) have achieved great success, yet their efficiency is hampered by the multiple steps of bi-directional attention. In fact, there exists notable redundancy in their computation: when sampling discrete tokens, the rich semantics contained in the continuous features are lost. Some existing works attempt to cache the features to approximate future features. However, they exhibit considerable approximation error under aggressive acceleration settings. We attribute this to their limited expressivity and the failure to account for sampling information. To fill this gap, we propose learning a lightweight model that incorporates both previous features and sampled tokens, and regresses the average velocity field of feature evolution. The model has moderate complexity that suffices to capture the subtle dynamics while keeping lightweight compared to the original base model. We apply our method to two representative MIGMs and tasks. In particular, on the state-of-the-art Lumina-DiMOO, it achieves over 4x acceleration of text-to-image generation while maintaining quality, significantly pushing the Pareto frontier of masked image generation. The code and model weights are available at https://github.com/Kaiwen-Zhu/MIGM-Shortcut.

---

### Accelerating Masked Image Generation by Learning Latent Controlled Dynamics

Authors: Kaiwen Zhu, Quansheng Zeng, Yuandong Pu, Shuo Cao, Xiaohui Li, Yi Xin, Qi Qin, Jiayang Li, Yu Qiao, Jinjin Gu, Yihao Liu
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.23996v1

Masked Image Generation Models (MIGMs) have achieved great success, yet their efficiency is hampered by the multiple steps of bi-directional attention. In fact, there exists notable redundancy in their computation: when sampling discrete tokens, the rich semantics contained in the continuous features are lost. Some existing works attempt to cache the features to approximate future features. However, they exhibit considerable approximation error under aggressive acceleration rates. We attribute this to their limited expressivity and the failure to account for sampling information. To fill this gap, we propose to learn a lightweight model that incorporates both previous features and sampled tokens, and regresses the average velocity field of feature evolution. The model has moderate complexity that suffices to capture the subtle dynamics while keeping lightweight compared to the original base model. We apply our method, MIGM-Shortcut, to two representative MIGM architectures and tasks. In particular, on the state-of-the-art Lumina-DiMOO, it achieves over 4x acceleration of text-to-image generation while maintaining quality, significantly pushing the Pareto frontier of masked image generation. The code and model weights are available at https://github.com/Kaiwen-Zhu/MIGM-Shortcut.

---

### MINT: Multimodal Imaging-to-Speech Knowledge Transfer for Early Alzheimer's Screening

Authors: Vrushank Ahire, Yogesh Kumar, Anouck Girard, M. A. Ganaie
Published: 2026-02-27
Categories: cs.LG, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2602.23994v2

Alzheimer's disease is a progressive neurodegenerative disorder in which mild cognitive impairment (MCI) precedes dementia. Structural MRI provides biomarkers but requires costly infrastructure, limiting population-scale deployment. Speech offers a non-invasive alternative, yet speech-only classifiers are developed independently of neuroimaging and lack biological grounding for CN-versus-MCI classification. We propose MINT (Multimodal Imaging-to-Speech Knowledge Transfer), a three-stage framework that transfers MRI-derived biomarker structure to speech during training. An MRI teacher defines a compact embedding space for CN-versus-MCI classification, while a residual projection head aligns speech representations to this space using a combined geometric loss. The frozen MRI classifier enables imaging-free inference. On ADNI-4, aligned speech achieves performance comparable to speech baselines, while multimodal fusion improves over MRI alone. Ablations identify dropout regularization and self-supervised pretraining as important design choices. To our knowledge, MINT is the first demonstration of MRI-to-speech knowledge transfer for early Alzheimer's screening without imaging at inference.

---

### MINT: Multimodal Imaging-to-Speech Knowledge Transfer for Early Alzheimer's Screening

Authors: Vrushank Ahire, Yogesh Kumar, Anouck Girard, M. A. Ganaie
Published: 2026-02-27
Categories: cs.LG, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2602.23994v1

Alzheimer's disease is a progressive neurodegenerative disorder in which mild cognitive impairment (MCI) marks a critical transition between aging and dementia. Neuroimaging modalities, such as structural MRI, provide biomarkers of this transition; however, their high costs and infrastructure needs limit their deployment at a population scale. Speech analysis offers a non-invasive alternative, but speech-only classifiers are developed independently of neuroimaging, leaving decision boundaries biologically ungrounded and limiting reliability on the subtle CN-versus-MCI distinction. We propose MINT (Multimodal Imaging-to-Speech Knowledge Transfer), a three-stage cross-modal framework that transfers biomarker structure from MRI into a speech encoder at training time. An MRI teacher, trained on 1,228 subjects, defines a compact neuroimaging embedding space for CN-versus-MCI classification. A residual projection head aligns speech representations to this frozen imaging manifold via a combined geometric loss, adapting speech to the learned biomarker space while preserving imaging encoder fidelity. The frozen MRI classifier, which is never exposed to speech, is applied to aligned embeddings at inference and requires no scanner. Evaluation on ADNI-4 shows aligned speech achieves performance comparable to speech-only baselines (AUC 0.720 vs 0.711) while requiring no imaging at inference, demonstrating that MRI-derived decision boundaries can ground speech representations. Multimodal fusion improves over MRI alone (0.973 vs 0.958). Ablation studies identify dropout regularization and self-supervised pretraining as critical design decisions. To our knowledge, this is the first demonstration of MRI-to-speech knowledge transfer for early Alzheimer's screening, establishing a biologically grounded pathway for population-level cognitive triage without neuroimaging at inference.

---

### The GRADIEND Python Package: An End-to-End System for Gradient-Based Feature Learning

Authors: Jonathan Drechsel, Steffen Herbold
Published: 2026-02-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.23993v3

We present gradiend, an open-source Python package that operationalizes the GRADIEND method for learning feature directions from factual-counterfactual MLM and CLM gradients in language models. The package provides a unified workflow for feature-related data creation, training, evaluation, visualization, persistent model rewriting via controlled weight updates, and multi-feature comparison. We demonstrate gradiend through an English pronoun running example, a semantic sentiment use case that evaluates lexical generalization to held-out target words, and a large-scale feature comparison.

---

### The GRADIEND Python Package: An End-to-End System for Gradient-Based Feature Learning

Authors: Jonathan Drechsel, Steffen Herbold
Published: 2026-02-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.23993v2

We present gradiend, an open-source Python package that operationalizes the GRADIEND method for learning feature directions from factual-counterfactual MLM and CLM gradients in language models. The package provides a unified workflow for feature-related data creation, training, evaluation, visualization, persistent model rewriting via controlled weight updates, and multi-feature comparison. We demonstrate gradiend through an English pronoun running example, a semantic sentiment use case that evaluates lexical generalization to held-out target words, and a large-scale feature comparison.

---

### Intrinsic Lorentz Neural Network

Authors: Xianglong Shi, Ziheng Chen, Yunhan Jiang, Nicu Sebe
Published: 2026-02-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.23981v1

Real-world data frequently exhibit latent hierarchical structures, which can be naturally represented by hyperbolic geometry. Although recent hyperbolic neural networks have demonstrated promising results, many existing architectures remain partially intrinsic, mixing Euclidean operations with hyperbolic ones or relying on extrinsic parameterizations. To address it, we propose the \emph{Intrinsic Lorentz Neural Network} (ILNN), a fully intrinsic hyperbolic architecture that conducts all computations within the Lorentz model. At its core, the network introduces a novel \emph{point-to-hyperplane} fully connected layer (FC), replacing traditional Euclidean affine logits with closed-form hyperbolic distances from features to learned Lorentz hyperplanes, thereby ensuring that the resulting geometric decision functions respect the inherent curvature. Around this fundamental layer, we design intrinsic modules: GyroLBN, a Lorentz batch normalization that couples gyro-centering with gyro-scaling, consistently outperforming both LBN and GyroBN while reducing training time. We additionally proposed a gyro-additive bias for the FC output, a Lorentz patch-concatenation operator that aligns the expected log-radius across feature blocks via a digamma-based scale, and a Lorentz dropout layer. Extensive experiments conducted on CIFAR-10/100 and two genomic benchmarks (TEB and GUE) illustrate that ILNN achieves state-of-the-art performance and computational cost among hyperbolic models and consistently surpasses strong Euclidean baselines. The code is available at \href{https://github.com/Longchentong/ILNN}{\textcolor{magenta}{this url}}.

---

### Venus: Benchmarking and Empowering Multimodal Large Language Models for Aesthetic Guidance and Cropping

Authors: Tianxiang Du, Hulingxiao He, Yuxin Peng
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.23980v1

The widespread use of smartphones has made photography ubiquitous, yet a clear gap remains between ordinary users and professional photographers, who can identify aesthetic issues and provide actionable shooting guidance during capture. We define this capability as aesthetic guidance (AG) -- an essential but largely underexplored domain in computational aesthetics. Existing multimodal large language models (MLLMs) primarily offer overly positive feedback, failing to identify issues or provide actionable guidance. Without AG capability, they cannot effectively identify distracting regions or optimize compositional balance, thus also struggling in aesthetic cropping, which aims to refine photo composition through reframing after capture. To address this, we introduce AesGuide, the first large-scale AG dataset and benchmark with 10,748 photos annotated with aesthetic scores, analyses, and guidance. Building upon it, we propose Venus, a two-stage framework that first empowers MLLMs with AG capability through progressively complex aesthetic questions and then activates their aesthetic cropping power via CoT-based rationales. Extensive experiments show that Venus substantially improves AG capability and achieves state-of-the-art (SOTA) performance in aesthetic cropping, enabling interpretable and interactive aesthetic refinement across both stages of photo creation. Code is available at https://github.com/PKU-ICST-MIPL/Venus_CVPR2026.

---

### Pessimistic Auxiliary Policy for Offline Reinforcement Learning

Authors: Fan Zhang, Baoru Huang, Xin Zhang
Published: 2026-02-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.23974v2

Offline reinforcement learning aims to learn an agent from pre-collected datasets, avoiding unsafe and inefficient real-time interaction. However, inevitable access to out-ofdistribution actions during the learning process introduces approximation errors, causing the error accumulation and considerable overestimation. In this paper, we construct a new pessimistic auxiliary policy for sampling reliable actions. Specifically, we develop a pessimistic auxiliary strategy by maximizing the lower confidence bound of the Q-function. The pessimistic auxiliary strategy exhibits a relatively high value and low uncertainty in the vicinity of the learned policy, avoiding the learned policy sampling high-value actions with potentially high errors during the learning process. Less approximation error introduced by sampled action from pessimistic auxiliary strategy leads to the alleviation of error accumulation. Extensive experiments on offline reinforcement learning benchmarks reveal that utilizing the pessimistic auxiliary strategy can effectively improve the efficacy of other offline RL approaches.

---

### Ask don't tell: Reducing sycophancy in large language models

Authors: Magda Dubois, Cozmin Ududec, Christopher Summerfield, Lennart Luettgau
Published: 2026-02-27
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2602.23971v4

Sycophancy, the tendency of large language models to favour user-affirming responses over critical engagement, has been identified as an alignment failure, particularly in high-stakes advisory and social contexts. While prior work has documented conversational features correlated with sycophancy, we lack a systematic understanding of what provokes or prevents AI sycophancy. Here, we present a set of controlled experimental studies where we first isolate how input framing influences sycophancy, and second, leverage these findings to develop mitigation strategies. In a nested factorial design, we compare questions to various non-questions where we vary three orthogonal factors: epistemic certainty (statement, belief, conviction), perspective (I- vs user-perspective), and affirmation vs negation. Measuring expressed sycophancy, how sycophantically a model phrases its free-text response, we show that (1) sycophancy is substantially higher in response to non-questions compared to questions. Additionally, we find that (2) sycophancy increases monotonically with epistemic certainty conveyed by the user, and (3) is amplified by I-perspective framing. Building on this, we show that asking a model to convert non-questions into questions before answering significantly reduces sycophancy. Importantly, this effect is stronger than a simple baseline prompt asking models "not to be sycophantic". In a follow-up experiment, we show that these framing effects generalise to choice sycophancy, which answer a model commits to, in a more context-rich, personalised setting: when a model is given extensive knowledge of a user and must select between forced binary choices, the same question vs. statement framing shapes how often it picks the answer aligned with the user's stance. Our work offers a practical and effective input-level mitigation that both developers and users can easily adopt.

---

### MSVBench: Towards Human-Level Evaluation of Multi-Shot Video Generation

Authors: Haoyuan Shi, Yunxin Li, Nanhao Deng, Zhenran Xu, Xinyu Chen, Longyue Wang, Baotian Hu, Min Zhang
Published: 2026-02-27
Categories: cs.MM, cs.CV
arXiv: https://arxiv.org/abs/2602.23969v1

The evolution of video generation toward complex, multi-shot narratives has exposed a critical deficit in current evaluation methods. Existing benchmarks remain anchored to single-shot paradigms, lacking the comprehensive story assets and cross-shot metrics required to assess long-form coherence and appeal. To bridge this gap, we introduce MSVBench, the first comprehensive benchmark featuring hierarchical scripts and reference images tailored for Multi-Shot Video generation. We propose a hybrid evaluation framework that synergizes the high-level semantic reasoning of Large Multimodal Models (LMMs) with the fine-grained perceptual rigor of domain-specific expert models. Evaluating 20 video generation methods across diverse paradigms, we find that current models--despite strong visual fidelity--primarily behave as visual interpolators rather than true world models. We further validate the reliability of our benchmark by demonstrating a state-of-the-art Spearman's rank correlation of 94.4% with human judgments. Finally, MSVBench extends beyond evaluation by providing a scalable supervisory signal. Fine-tuning a lightweight model on its pipeline-refined reasoning traces yields human-aligned performance comparable to commercial models like Gemini-2.5-Flash.

---

### Learning Generation Orders for Masked Discrete Diffusion Models via Variational Inference

Authors: David Fox, Sam Bowyer, Song Liu, Laurence Aitchison, Raul Santos-Rodriguez, Mengyue Yang
Published: 2026-02-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.23968v1

Masked discrete diffusion models (MDMs) are a promising new approach to generative modelling, offering the ability for parallel token generation and therefore greater efficiency than autoregressive counterparts. However, achieving an optimal balance between parallel generation and sample quality remains an open problem. Current approaches primarily address this issue through fixed, heuristic parallel sampling methods. There exist some recent learning based approaches to this problem, but its formulation from the perspective of variational inference remains underexplored. In this work, we propose a variational inference framework for learning parallel generation orders for MDMs. As part of our method, we propose a parameterisation for the approximate posterior of generation orders which facilitates parallelism and efficient sampling during training. Using this method, we conduct preliminary experiments on the GSM8K dataset, where our method performs competitively against heuristic sampling strategies in the regime of highly parallel generation. For example, our method achieves 33.1\% accuracy with an average of only only 4 generation steps, compared to 23.7-29.0\% accuracy achieved by standard competitor methods in the same number of steps. We believe further experiments and analysis of the method will yield valuable insights into the problem of parallel generation with MDMs.

---

### SpikeTrack: A Spike-driven Framework for Efficient Visual Tracking

Authors: Qiuyang Zhang, Jiujun Cheng, Qichao Mao, Cong Liu, Yu Fang, Yuhong Li, Mengying Ge, Shangce Gao
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.23963v1

Spiking Neural Networks (SNNs) promise energy-efficient vision, but applying them to RGB visual tracking remains difficult: Existing SNN tracking frameworks either do not fully align with spike-driven computation or do not fully leverage neurons' spatiotemporal dynamics, leading to a trade-off between efficiency and accuracy. To address this, we introduce SpikeTrack, a spike-driven framework for energy-efficient RGB object tracking. SpikeTrack employs a novel asymmetric design that uses asymmetric timestep expansion and unidirectional information flow, harnessing spatiotemporal dynamics while cutting computation. To ensure effective unidirectional information transfer between branches, we design a memory-retrieval module inspired by neural inference mechanisms. This module recurrently queries a compact memory initialized by the template to retrieve target cues and sharpen target perception over time. Extensive experiments demonstrate that SpikeTrack achieves the state-of-the-art among SNN-based trackers and remains competitive with advanced ANN trackers. Notably, it surpasses TransT on LaSOT dataset while consuming only 1/26 of its energy. To our knowledge, SpikeTrack is the first spike-driven framework to make RGB tracking both accurate and energy efficient. The code and models are available at https://github.com/faicaiwawa/SpikeTrack.

---

### Extending 2D foundational DINOv3 representations to 3D segmentation of neonatal brain MR images

Authors: Annayah Usman, Behraj Khan, Tahir Qasim Syed
Published: 2026-02-27
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2602.23962v1

Precise volumetric delineation of hippocampal structures is essential for quantifying neurodevelopmental trajectories in pre-term and term infants, where subtle morphological variations may carry prognostic significance. While foundation encoders trained on large-scale visual data offer discriminative representations, their 2D formulation is a limitation with respect to the $3$D organization of brain anatomy. We propose a volumetric segmentation strategy that reconciles this tension through a structured window-based disassembly-reassembly mechanism: the global MRI volume is decomposed into non-overlapping 3D windows or sub-cubes, each processed via a separate decoding arm built upon frozen high-fidelity features, and subsequently reassembled prior to a ground-truth correspendence using a dense-prediction head. This architecture preserves constant a decoder memory footprint while forcing predictions to lie within an anatomically consistent geometry. Evaluated on the ALBERT dataset for hippocampal segmentation, the proposed approach achieves a Dice score of 0.65 for a single 3D window. The method demonstrates that volumetric anatomical structure could be recovered from frozen 2D foundation representations through structured compositional decoding, and offers a principled and generalizable extension for foundation models for 3D medical applications.

---

### Clinically-aligned ischemic stroke segmentation and ASPECTS scoring on NCCT imaging using a slice-gated loss on foundation representations

Authors: Hiba Azeem, Behraj Khan, Tahir Qasim Syed
Published: 2026-02-27
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2602.23961v1

Rapid infarct assessment on non-contrast CT (NCCT) is essential for acute ischemic stroke management. Most deep learning methods perform pixel-wise segmentation without modeling the structured anatomical reasoning underlying ASPECTS scoring, where basal ganglia (BG) and supraganglionic (SG) levels are clinically interpreted in a coupled manner. We propose a clinically aligned framework that combines a frozen DINOv3 backbone with a lightweight decoder and introduce a Territory-Aware Gated Loss (TAGL) to enforce BG-SG consistency during training. This anatomically informed supervision adds no inference-time complexity. Our method achieves a Dice score of 0.6385 on AISD, outperforming prior CNN and foundation-model baselines. On a proprietary ASPECTS dataset, TAGL improves mean Dice from 0.698 to 0.767. These results demonstrate that integrating foundation representations with structured clinical priors improves NCCT stroke segmentation and ASPECTS delineation.

---

### SHINE: Sequential Hierarchical Integration Network for EEG and MEG

Authors: Xiran Xu, Yujie Yan, Songyi Li, Linze Zheng, Zifeng Zhang, Mochu Dong, Jing Chen
Published: 2026-02-27
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2602.23960v2

How natural speech is represented in the brain constitutes a major challenge for cognitive neuroscience. Reconstructing the speech envelope and Mel spectrogram from EEG and MEG provides a time-resolved way to study its temporal and spectral structure. Speech-related neural activity spans sensors and temporal scales; extracting these representations while adapting the use of context to each acoustic target is a central problem in speech reconstruction. We propose SHINE, a Sequential Hierarchical Integration Network for EEG and MEG. A residual sensor adapter unifies input dimensions, intermediate dilated-block states retain temporal depth, and a target- and time-dependent gate fuses local hierarchical and attention-enhanced context predictions. Across two EEG and two MEG datasets, SHINE has the highest mean envelope and mean-Mel Pearson correlations among nine local baseline implementations on all eight dataset-metric combinations. SHINE also placed second in the speech-detection Extended Track of the NeurIPS 2025 PNPL Competition. Code will be released at https://github.com/xuxiran/SHINE.

---

### SHINE: Sequential Hierarchical Integration Network for EEG and MEG

Authors: Xiran Xu, Yujie Yan, Xihong Wu, Jing Chen
Published: 2026-02-27
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2602.23960v1

How natural speech is represented in the brain constitutes a major challenge for cognitive neuroscience, with cortical envelope-following responses playing a central role in speech decoding. This paper presents our approach to the Speech Detection task in the LibriBrain Competition 2025, utilizing over 50 hours of magnetoencephalography (MEG) signals from a single participant listening to LibriVox audiobooks. We introduce the proposed Sequential Hierarchical Integration Network for EEG and MEG (SHINE) to reconstruct the binary speech-silence sequences from MEG signals. In the Extended Track, we further incorporated auxiliary reconstructions of speech envelopes and Mel spectrograms to enhance training. Ensemble methods combining SHINE with baselines (BrainMagic, AWavNet, ConvConcatNet) achieved F1-macro scores of 0.9155 (Standard Track) and 0.9184 (Extended Track) on the leaderboard test set.

---

### Thinking with Images as Continuous Actions: Numerical Visual Chain-of-Thought

Authors: Kesen Zhao, Beier Zhu, Junbao Zhou, Xingyu Zhu, Zhongqi Yue, Hanwang Zhang
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.23959v1

Recent multimodal large language models (MLLMs) increasingly rely on visual chain-of-thought to perform region-grounded reasoning over images. However, existing approaches ground regions via either textified coordinates-causing modality mismatch and semantic fragmentation or fixed-granularity patches that both limit precise region selection and often require non-trivial architectural changes. In this paper, we propose Numerical Visual Chain-of-Thought (NV-CoT), a framework that enables MLLMs to reason over images using continuous numerical coordinates. NV-CoT expands the MLLM action space from discrete vocabulary tokens to a continuous Euclidean space, allowing models to directly generate bounding-box coordinates as actions with only minimal architectural modification. The framework supports both supervised fine-tuning and reinforcement learning. In particular, we replace categorical token policies with a Gaussian (or Laplace) policy over coordinates and introduce stochasticity via reparameterized sampling, making NV-CoT fully compatible with GRPO-style policy optimization. Extensive experiments on three benchmarks against eight representative visual reasoning baselines demonstrate that NV-CoT significantly improves localization precision and final answer accuracy, while also accelerating training convergence, validating the effectiveness of continuous-action visual reasoning in MLLMs. The code is available in https://github.com/kesenzhao/NV-CoT.

---

### SwitchCraft: Training-Free Multi-Event Video Generation with Attention Controls

Authors: Qianxun Xu, Chenxi Song, Yujun Cai, Chi Zhang
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.23956v2

Recent advances in text-to-video diffusion models have enabled high-fidelity and temporally coherent videos synthesis. However, current models are predominantly optimized for single-event generation. When handling multi-event prompts, without explicit temporal grounding, such models often produce blended or collapsed scenes that break the intended narrative. To address this limitation, we present SwitchCraft, a training-free framework for multi-event video generation. Our key insight is that uniform prompt injection across time ignores the correspondence between events and frames. To this end, we introduce Event-Aligned Query Steering (EAQS), which steers frame-level attention to align with relevant event prompts. Furthermore, we propose Auto-Balance Strength Solver (ABSS), which adaptively balances steering strength to preserve temporal consistency and visual fidelity. Extensive experiments demonstrate that SwitchCraft substantially improves prompt alignment, event clarity, and scene consistency compared with existing baselines, offering a simple yet effective solution for multi-event video generation.

---

### GDA-YOLO11: Amodal Instance Segmentation for Occlusion-Robust Robotic Fruit Harvesting

Authors: Caner Beldek, Emre Sariyildiz, Son Lam Phung, Gursel Alici
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.23953v1

Occlusion remains a critical challenge in robotic fruit harvesting, as undetected or inaccurately localised fruits often results in substantial crop losses. To mitigate this issue, we propose a harvesting framework using a new amodal segmentation model, GDA-YOLO11, which incorporates architectural improvements and an updated asymmetric mask loss. The proposed model is trained on a modified version of a public citrus dataset and evaluated on both the base dataset and occlusion-sensitive subsets with varying occlusion levels. Within the framework, full fruit masks, including invisible regions, are inferred by GDA-YOLO11, and picking points are subsequently estimated using the Euclidean distance transform. These points are then projected into 3D coordinates for robotic harvesting execution. Experiments were conducted using real citrus fruits in a controlled environment simulating occlusion scenarios. Notably, to the best of our knowledge, this study provides the first practical demonstration of amodal instance segmentation in robotic fruit harvesting. GDA-YOLO11 achieves a precision of 0.844, recall of 0.846, mAP@50 of 0.914, and mAP@50:95 of 0.636, outperforming YOLO11n by 5.1%, 1.3%, and 1.0% in precision, mAP@50, and mAP@50:95, respectively. The framework attains harvesting success rates of 92.59%, 85.18%, 48.14%, and 22.22% at zero to high occlusion levels, improving success by 3.5% under medium and high occlusion. These findings demonstrate that GDA-YOLO11 enhances occlusion robust segmentation and streamlines perception-to-action integration, paving the way for more reliable autonomous systems in agriculture.

---

### CC-VQA: Conflict- and Correlation-Aware Method for Mitigating Knowledge Conflict in Knowledge-Based Visual Question Answering

Authors: Yuyang Hong, Jiaqi Gu, Yujin Lou, Lubin Fan, Qi Yang, Ying Wang, Kun Ding, Yue Wu, Shiming Xiang, Jieping Ye
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.23952v1

Knowledge-based visual question answering (KB-VQA) demonstrates significant potential for handling knowledge-intensive tasks. However, conflicts arise between static parametric knowledge in vision language models (VLMs) and dynamically retrieved information due to the static model knowledge from pre-training. The outputs either ignore retrieved contexts or exhibit inconsistent integration with parametric knowledge, posing substantial challenges for KB-VQA. Current knowledge conflict mitigation methods primarily adapted from language-based approaches, focusing on context-level conflicts through engineered prompting strategies or context-aware decoding mechanisms. However, these methods neglect the critical role of visual information in conflicts and suffer from redundant retrieved contexts, which impair accurate conflict identification and effective mitigation. To address these limitations, we propose \textbf{CC-VQA}: a novel training-free, conflict- and correlation-aware method for KB-VQA. Our method comprises two core components: (1) Vision-Centric Contextual Conflict Reasoning, which performs visual-semantic conflict analysis across internal and external knowledge contexts; and (2) Correlation-Guided Encoding and Decoding, featuring positional encoding compression for low-correlation statements and adaptive decoding using correlation-weighted conflict scoring. Extensive evaluations on E-VQA, InfoSeek, and OK-VQA benchmarks demonstrate that CC-VQA achieves state-of-the-art performance, yielding absolute accuracy improvements of 3.3\% to 6.4\% compared to existing methods. Code is available at https://github.com/cqu-student/CC-VQA.

---

### AHAP: Reconstructing Arbitrary Humans from Arbitrary Perspectives with Geometric Priors

Authors: Xiaozhen Qiao, Wenjia Wang, Zhiyuan Zhao, Jiacheng Sun, Ping Luo, Hongyuan Zhang, Xuelong Li
Published: 2026-02-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.23951v2

Reconstructing 3D humans from images captured at multiple perspectives typically requires pre-calibration, like using checkerboards or MVS algorithms, which limits scalability and applicability in diverse real-world scenarios. In this work, we present AHAP (Reconstructing Arbitrary Humans from Arbitrary Perspectives), a feed-forward framework for reconstructing arbitrary humans from arbitrary camera perspectives without requiring camera calibration. Our core lies in the effective fusion of multi-view geometry to assist human association, reconstruction and localization. Specifically, we use a Cross-View Identity Association module through learnable person queries and soft assignment, supervised by contrastive learning to resolve cross-view human identity association. A Human Head fuses cross-view features and scene context for SMPL prediction, guided by cross-view reprojection losses to enforce body pose consistency. Additionally, multi-view geometry eliminates the depth ambiguity inherent in monocular methods, providing more precise 3D human localization through multi-view triangulation. Experiments on EgoHumans and EgoExo4D demonstrate that AHAP achieves competitive performance on both world-space human reconstruction and camera pose estimation, while being 180$\times$ faster than optimization-based approaches.

---

### Micro-expression Recognition Based on Dual-branch Feature Extraction and Fusion

Authors: Mingjie Zhang, Bo Li, Wanting Liu, Hongyan Cui, Yue Li, Qingwen Li, Hong Li, Ge Gao
Published: 2026-02-27
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.23950v1

Micro-expressions, characterized by transience and subtlety, pose challenges to existing optical flow-based recognition methods. To address this, this paper proposes a dual-branch micro-expression feature extraction network integrated with parallel attention. Key contributions include: 1) a residual network designed to alleviate gradient anishing and network degradation; 2) an Inception network constructed to enhance model representation and suppress interference from irrelevant regions; 3) an adaptive feature fusion module developed to integrate dual-branch features. Experiments on the CASME II dataset demonstrate that the proposed method achieves 74.67% accuracy, outperforming LBP-TOP (by 11.26%), MSMMT (by 3.36%), and other comparative methods.

---

### HotelQuEST: Balancing Quality and Efficiency in Agentic Search

Authors: Guy Hadad, Shadi Iskander, Oren Kalinsky, Sofia Tolmach, Ran Levy, Haggai Roitman
Published: 2026-02-27
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2602.23949v1

Agentic search has emerged as a promising paradigm for adaptive retrieval systems powered by large language models (LLMs). However, existing benchmarks primarily focus on quality, overlooking efficiency factors that are critical for real-world deployment. Moreover, real-world user queries often contain underspecified preferences, a challenge that remains largely underexplored in current agentic search evaluation. As a result, many agentic search systems remain impractical despite their impressive performance. In this work, we introduce HotelQuEST, a benchmark comprising 214 hotel search queries that range from simple factual requests to complex queries, enabling evaluation across the full spectrum of query difficulty. We further address the challenge of evaluating underspecified user preferences by collecting clarifications that make annotators' implicit preferences explicit for evaluation. We find that LLM-based agents achieve higher accuracy than traditional retrievers, but at substantially higher costs due to redundant tool calls and suboptimal routing that fails to match query complexity to model capability. Our analysis exposes inefficiencies in current agentic search systems and demonstrates substantial potential for cost-aware optimization.

---

### Hierarchical Concept-based Interpretable Models

Authors: Oscar Hill, Mateo Espinosa Zarlenga, Mateja Jamnik
Published: 2026-02-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.23947v1

Modern deep neural networks remain challenging to interpret due to the opacity of their latent representations, impeding model understanding, debugging, and debiasing. Concept Embedding Models (CEMs) address this by mapping inputs to human-interpretable concept representations from which tasks can be predicted. Yet, CEMs fail to represent inter-concept relationships and require concept annotations at different granularities during training, limiting their applicability. In this paper, we introduce Hierarchical Concept Embedding Models (HiCEMs), a new family of CEMs that explicitly model concept relationships through hierarchical structures. To enable HiCEMs in real-world settings, we propose Concept Splitting, a method for automatically discovering finer-grained sub-concepts from a pretrained CEM's embedding space without requiring additional annotations. This allows HiCEMs to generate fine-grained explanations from limited concept labels, reducing annotation burdens. Our evaluation across multiple datasets, including a user study and experiments on PseudoKitchens, a newly proposed concept-based dataset of 3D kitchen renders, demonstrates that (1) Concept Splitting discovers human-interpretable sub-concepts absent during training that can be used to train highly accurate HiCEMs, and (2) HiCEMs enable powerful test-time concept interventions at different granularities, leading to improved task accuracy.

---

### PointCoT: A Multi-modal Benchmark for Explicit 3D Geometric Reasoning

Authors: Dongxu Zhang, Yiding Sun, Pengcheng Li, Yumou Liu, Hongqiang Lin, Haoran Xu, Xiaoxuan Mu, Liang Lin, Wenbiao Yan, Ning Yang, Chaowei Fang, Juanjuan Zhao et al.
Published: 2026-02-27
Categories: cs.CV, cs.AI, cs.MM
arXiv: https://arxiv.org/abs/2602.23945v1

While Multimodal Large Language Models (MLLMs) demonstrate proficiency in 2D scenes, extending their perceptual intelligence to 3D point cloud understanding remains a significant challenge. Current approaches focus primarily on aligning 3D features with pre-trained models. However, they typically treat geometric reasoning as an implicit mapping process. These methods bypass intermediate logical steps and consequently suffer from geometric hallucinations. They confidently generate plausible responses that fail to ground in precise structural details. To bridge this gap, we present PointCoT, a novel framework that empowers MLLMs with explicit Chain-of-Thought (CoT) reasoning for 3D data. We advocate for a \textit{Look, Think, then Answer} paradigm. In this approach, the model is supervised to generate geometry-grounded rationales before predicting final answers. To facilitate this, we construct Point-Reason-Instruct, a large-scale benchmark comprising $\sim$86k instruction-tuning samples with hierarchical CoT annotations. By leveraging a dual-stream multi-modal architecture, our method synergizes semantic appearance with geometric truth. Extensive experiments demonstrate that PointCoT achieves state-of-the-art performance on complex reasoning tasks.

---

### MemEmo: Evaluating Emotion in Memory Systems of Agents

Authors: Peng Liu, Zhen Tao, Jihao Zhao, Ding Chen, Yansong Zhang, Cuiping Li, Zhiyu Li, Hong Chen
Published: 2026-02-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.23944v1

Memory systems address the challenge of context loss in Large Language Model during prolonged interactions. However, compared to human cognition, the efficacy of these systems in processing emotion-related information remains inconclusive. To address this gap, we propose an emotion-enhanced memory evaluation benchmark to assess the performance of mainstream and state-of-the-art memory systems in handling affective information. We developed the \textbf{H}uman-\textbf{L}ike \textbf{M}emory \textbf{E}motion (\textbf{HLME}) dataset, which evaluates memory systems across three dimensions: emotional information extraction, emotional memory updating, and emotional memory question answering. Experimental results indicate that none of the evaluated systems achieve robust performance across all three tasks. Our findings provide an objective perspective on the current deficiencies of memory systems in processing emotional memories and suggest a new trajectory for future research and system optimization.

---

### EDDA-Coordinata: An Annotated Dataset of Historical Geographic Coordinates

Authors: Ludovic Moncla, Pierre Nugues, Thierry Joliveau, Katherine McDonough
Published: 2026-02-27
Categories: cs.CL, cs.DL, cs.IR
arXiv: https://arxiv.org/abs/2602.23941v1

This paper introduces a dataset of enriched geographic coordinates retrieved from Diderot and d'Alembert's eighteenth-century Encyclopedie. Automatically recovering geographic coordinates from historical texts is a complex task, as they are expressed in a variety of ways and with varying levels of precision. To improve retrieval of coordinates from similar digitized early modern texts, we have created a gold standard dataset, trained models, published the resulting inferred and normalized coordinate data, and experimented applying these models to new texts. From 74,000 total articles in each of the digitized versions of the Encyclopedie from ARTFL and ENCCRE, we examined 15,278 geographical entries, manually identifying 4,798 containing coordinates, and 10,480 with descriptive but non-numerical references. Leveraging our gold standard annotations, we trained transformer-based models to retrieve and normalize coordinates. The pipeline presented here combines a classifier to identify coordinate-bearing entries and a second model for retrieval, tested across encoder-decoder and decoder architectures. Cross-validation yielded an 86% EM score. On an out-of-domain eighteenth-century Trevoux dictionary (also in French), our fine-tuned model had a 61% EM score, while for the nineteenth-century, 7th edition of the Encyclopaedia Britannica in English, the EM was 77%. These findings highlight the gold standard dataset's usefulness as training data, and our two-step method's cross-lingual, cross-domain generalizability.

---