# Research Papers — 2026-02 · bundle page 113 of 210 > Full-text markdown of papers #5601–5650 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/113 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/112.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/114.md) ### Simultaneous Speech-to-Speech Translation Without Aligned Data Authors: Tom Labiausse, Romain Fabre, Yannick Estève, Alexandre Défossez, Neil Zeghidour Published: 2026-02-11 Categories: cs.CL, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2602.11072v2 Simultaneous speech translation requires translating source speech into a target language in real-time while handling non-monotonic word dependencies. Traditional approaches rely on supervised training with word-level aligned data, which is difficult to collect at scale and thus depends on synthetic alignments using language-specific heuristics that are suboptimal. We propose Hibiki-Zero, which eliminates the need for word-level alignments entirely. This fundamentally simplifies the training pipeline and enables seamless scaling to diverse languages with varying grammatical structures, removing the bottleneck of designing language-specific alignment heuristics. We first train on sentence-level aligned data to learn speech translation at high latency, then apply a novel reinforcement learning strategy using GRPO to optimize latency while preserving translation quality. Hibiki-Zero achieves state-of-the-art performance in translation accuracy, latency, voice transfer, and naturalness across five X-to-English tasks. Moreover, we demonstrate that our model can be adapted to support a new input language with less than 1000h of speech. We provide examples, model weights, inference code and we release a benchmark containing 45h of multilingual data for speech translation evaluation. --- ### PuriLight: A Lightweight Shuffle and Purification Framework for Monocular Depth Estimation Authors: Yujie Chen, Li Zhang, Xiaomeng Chu, Tian Zhang Published: 2026-02-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.11066v1 We propose PuriLight, a lightweight and efficient framework for self-supervised monocular depth estimation, to address the dual challenges of computational efficiency and detail preservation. While recent advances in self-supervised depth estimation have reduced reliance on ground truth supervision, existing approaches remain constrained by either bulky architectures compromising practicality or lightweight models sacrificing structural precision. These dual limitations underscore the critical need to develop lightweight yet structurally precise architectures. Our framework addresses these limitations through a three-stage architecture incorporating three novel modules: the Shuffle-Dilation Convolution (SDC) module for local feature extraction, the Rotation-Adaptive Kernel Attention (RAKA) module for hierarchical feature enhancement, and the Deep Frequency Signal Purification (DFSP) module for global feature purification. Through effective collaboration, these modules enable PuriLight to achieve both lightweight and accurate feature extraction and processing. Extensive experiments demonstrate that PuriLight achieves state-of-the-art performance with minimal training parameters while maintaining exceptional computational efficiency. Codes will be available at https://github.com/ishrouder/PuriLight. --- ### S-MARC: Causal Streaming Reasoning for Full-Duplex Conversational Behavior Modeling Authors: Dingkun Zhou, Shuchang Pan, Jiachen Lian, Siddharth Banerjee, Sarika Pasumarthy, Dhruv Hebbar, Siddhant Patel, Zeyi Austin Li, Kan Jen Cheng, Sanay Bordia, Krish Patel, Akshaj Gupta et al. Published: 2026-02-11 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.11065v2 Human conversation is organized by an implicit chain of thought and manifests as temporally structured conversational behaviors. Capturing this perceptual pathway is critical for building natural full-duplex interactive systems. We propose S-MARC (Streaming Causal Modeling and Reasoning for Conversation), a streaming, causal, and hierarchical framework for conversational behavior modeling and reasoning. By formalizing the intent-to-action pathway, S-MARC predicts high-level communicative functions and low-level interaction behaviors while modeling their causal and temporal dependencies. To support this setting, we construct a high-quality corpus that pairs controllable, event-rich duplex dialogue data with behavior labels. S-MARC organizes streaming predictions into a continuously evolving graph structure, generates concise justifications for its decisions, and dynamically optimizes its reasoning process. Experiments on synthetic and real duplex dialogues show that S-MARC achieves robust behavior detection, produces interpretable reasoning chains, and establishes a benchmark foundation for conversational reasoning in full-duplex spoken dialogue systems. --- ### Motion Capture is Not the Target Domain: Scaling Synthetic Data for Learning Motion Representations Authors: Firas Darwish, George Nicholson, Aiden Doherty, Hang Yuan Published: 2026-02-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.11064v1 Synthetic data offers a compelling path to scalable pretraining when real-world data is scarce, but models pretrained on synthetic data often fail to transfer reliably to deployment settings. We study this problem in full-body human motion, where large-scale data collection is infeasible but essential for wearable-based Human Activity Recognition (HAR), and where synthetic motion can be generated from motion-capture-derived representations. We pretrain motion time-series models using such synthetic data and evaluate their transfer across diverse downstream HAR tasks. Our results show that synthetic pretraining improves generalisation when mixed with real data or scaled sufficiently. We also demonstrate that large-scale motion-capture pretraining yields only marginal gains due to domain mismatch with wearable signals, clarifying key sim-to-real challenges and the limits and opportunities of synthetic motion data for transferable HAR representations. --- ### MoToRec: Sparse-Regularized Multimodal Tokenization for Cold-Start Recommendation Authors: Jialin Liu, Zhaorui Zhang, Ray C. C. Cheung Published: 2026-02-11 Categories: cs.LG, cs.IR arXiv: https://arxiv.org/abs/2602.11062v2 Graph neural networks (GNNs) have revolutionized recommender systems by effectively modeling complex user-item interactions, yet data sparsity and the item cold-start problem significantly impair performance, particularly for new items with limited or no interaction history. While multimodal content offers a promising solution, existing methods result in suboptimal representations for new items due to noise and entanglement in sparse data. To address this, we transform multimodal recommendation into discrete semantic tokenization. We present Sparse-Regularized Multimodal Tokenization for Cold-Start Recommendation (MoToRec), a framework centered on a sparsely-regularized Residual Quantized Variational Autoencoder (RQ-VAE) that generates a compositional semantic code of discrete, interpretable tokens, promoting disentangled representations. MoToRec's architecture is enhanced by three synergistic components: (1) a sparsely-regularized RQ-VAE that promotes disentangled representations, (2) a novel adaptive rarity amplification that promotes prioritized learning for cold-start items, and (3) a hierarchical multi-source graph encoder for robust signal fusion with collaborative signals. Extensive experiments on three large-scale datasets demonstrate MoToRec's superiority over state-of-the-art methods in both overall and cold-start scenarios. Our work validates that discrete tokenization provides an effective and scalable alternative for mitigating the long-standing cold-start challenge. --- ### A Gibbs posterior sampler for inverse problem based on prior diffusion model Authors: Jean-François Giovannelli Published: 2026-02-11 Categories: stat.ML, cs.LG, stat.AP arXiv: https://arxiv.org/abs/2602.11059v2 This paper addresses the issue of inversion in cases where (1) the observation system is modeled by a linear transformation and additive error, (2) the problem is ill-posed and regularization relies on a Bayesian strategy, (3)~the prior is modeled by a diffusion process adjusted on an available large set of examples. In this context, it is known that the issue of posterior sampling is a thorny one and the paper introduces a Gibbs algorithm. It appears that this avenue has not been explored, and we show that it is particularly effective and remarkably simple. In addition, it provides clear elements regarding convergence guarantees in a specific case and arguments supporting such guarantees in practical cases. The results are clearly confirmed by numerical simulations based on a toy example. --- ### Divide, Harmonize, Then Conquer It: Shooting Multi-Commodity Flow Problems with Multimodal Language Models Authors: Xinyu Yuan, Yan Qiao, Zonghui Wang, Wenzhi Chen Published: 2026-02-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.11057v1 The multi-commodity flow (MCF) problem is a fundamental topic in network flow and combinatorial optimization, with broad applications in transportation, communication, and logistics, etc. Nowadays, the rapid expansion of allocation systems has posed challenges for existing optimization engines in balancing optimality and tractability. In this paper, we present Pram, the first ML-based method that leverages the reasoning power of multimodal language models (MLMs) for addressing the trade-off dilemma -- a great need of service providers. As part of our proposal, Pram (i) quickly computes high-quality allocations by dividing the original problem into local subproblems, which are then resolved by an MLM-powered "agent", and (ii) ensures global consistency by harmonizing these subproblems via a multi-agent reinforcement learning algorithm. Theoretically, we show that Pram, which learns to perform gradient descent in context, provably converges to the optimum within the family of MCF problems. Empirically, on real-world datasets and public topologies, Pram achieves performance comparable to, and in some cases even surpassing, linear programming solvers (very close to the optimal solution), and substantially lower runtimes (1 to 2 orders of magnitude faster). Moreover, Pram exhibits strong robustness (<10\% performance degradation under link failures or flow bursts), demonstrating MLM's generalization ability to unforeseen events. Pram is objective-agnostic and seamlessly integrates with mainstream allocation systems, providing a practical and scalable solution for future networks. --- ### GraphSeek: Next-Generation Graph Analytics with LLMs Authors: Maciej Besta, Łukasz Jarmocik, Orest Hrycyna, Shachar Klaiman, Konrad Mączka, Robert Gerstenberger, Jürgen Müller, Piotr Nyczyk, Hubert Niewiadomski, Torsten Hoefler Published: 2026-02-11 Categories: cs.DB, cs.AI, cs.CL, cs.HC, cs.IR arXiv: https://arxiv.org/abs/2602.11052v2 Graphs are foundational across domains but remain hard to use without deep expertise. LLMs promise accessible natural language (NL) graph analytics, yet they fail to process industry-scale property graphs effectively and efficiently: such datasets are large, highly heterogeneous, structurally complex, and evolve dynamically. To address this, we devise a novel abstraction for complex multi-query analytics over such graphs. Its key idea is to replace brittle generation of graph queries directly from NL with planning over a Semantic Catalog that describes both the graph schema and the graph operations. Concretely, this induces a clean separation between a Semantic Plane for LLM planning and broader reasoning, and an Execution Plane for deterministic, database-grade query execution over the full dataset and tool implementations. This design yields substantial gains in both token efficiency and task effectiveness even with small-context LLMs. We use this abstraction as the basis of the first LLM-enhanced graph analytics framework called GraphSeek. GraphSeek achieves substantially higher success rates (e.g., 86% over enhanced LangChain) and points toward the next generation of affordable and accessible graph analytics that unify LLM reasoning with database-grade execution over large and complex property graphs. --- ### Embedding Inversion via Conditional Masked Diffusion Language Models Authors: Han Xiao Published: 2026-02-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.11047v3 We frame embedding inversion as conditional masked diffusion, recovering all tokens in parallel through iterative denoising rather than sequential autoregressive generation. A masked diffusion language model is conditioned on the target embedding via adaptive layer normalization, requiring only 8 forward passes with no access to the target encoder at inference time. On 32-token sequences across three embedding models, the method achieves token recovery through parallel denoising without requiring encoder access, iterative correction, or architecture-specific alignment. Source code and live demo are available at https://github.com/jina-ai/embedding-inversion-demo. --- ### Language Model Inversion through End-to-End Differentiation Authors: Kevin Yandoka Denamganaï, Kartic Subr Published: 2026-02-11 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.11044v1 Despite emerging research on Language Models (LM), few approaches analyse the invertibility of LMs. That is, given a LM and a desirable target output sequence of tokens, determining what input prompts would yield the target output remains an open problem. We formulate this problem as a classical gradient-based optimisation. First, we propose a simple algorithm to achieve end-to-end differentiability of a given (frozen) LM and then find optimised prompts via gradient descent. Our central insight is to view LMs as functions operating on sequences of distributions over tokens (rather than the traditional view as functions on sequences of tokens). Our experiments and ablations demonstrate that our DLM-powered inversion can reliably and efficiently optimise prompts of lengths $10$ and $80$ for targets of length $20$, for several white-box LMs (out-of-the-box). --- ### Characterizing Trainability of Instantaneous Quantum Polynomial Circuit Born Machines Authors: Kevin Shen, Susanne Pielawa, Vedran Dunjko, Hao Wang Published: 2026-02-11 Categories: quant-ph, cs.LG arXiv: https://arxiv.org/abs/2602.11042v2 Instantaneous quantum polynomial quantum circuit Born machines (IQP-QCBMs) have been proposed as quantum generative models with a classically tractable training objective based on the maximum mean discrepancy (MMD) and a potential quantum advantage motivated by sampling-complexity arguments, making them an exciting model worth deeper investigation. While recent works have further proven the universality of a (slightly generalized) model, the next immediate question pertains to its trainability, i.e., whether it suffers from the exponentially vanishing loss gradients, known as the barren plateau issue, preventing effective use, and how regimes of trainability overlap with regimes of possible quantum advantage. Here, we provide significant strides in these directions. To study the trainability at initialization, we analytically derive closed-form expressions for the variances of the partial derivatives of the MMD loss function and provide general upper and lower bounds. With uniform initialization, we show that barren plateaus depend on the generator set and the spectrum of the chosen kernel. We identify regimes in which low-weight-biased kernels avoid exponential gradient suppression in structured topologies. Also, we prove that a small-variance Gaussian initialization ensures polynomial scaling for the gradient under mild conditions. As for the potential quantum advantage, we further argue, based on previous complexity-theoretic arguments, that sparse IQP families can output a probability distribution family that is classically intractable, and that this distribution remains trainable at initialization at least at lower-weight frequencies. --- ### Learning Page Order in Shuffled WOO Releases Authors: Efe Kahraman, Giulio Tosato Published: 2026-02-11 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2602.11040v2 We investigate document page ordering on 5,461 shuffled WOO documents (Dutch freedom of information releases) using page embeddings. These documents are heterogeneous collections such as emails, legal texts, and spreadsheets compiled into single PDFs, where semantic ordering signals are unreliable. We compare five methods, including pointer networks, seq2seq transformers, and specialized pairwise ranking models. The best performing approach successfully reorders documents up to 15 pages, with Kendall's tau ranging from 0.95 for short documents (2-5 pages) to 0.72 for 15 page documents. We observe two unexpected failures: seq2seq transformers fail to generalize on long documents (Kendall's tau drops from 0.918 on 2-5 pages to 0.014 on 21-25 pages), and curriculum learning underperforms direct training by 39% on long documents. Ablation studies suggest learned positional encodings are one contributing factor to seq2seq failure, though the degradation persists across all encoding variants, indicating multiple interacting causes. Attention pattern analysis reveals that short and long documents require fundamentally different ordering strategies, explaining why curriculum learning fails. Model specialization achieves substantial improvements on longer documents (+0.21 tau). --- ### Linguistic Indicators of Early Cognitive Decline in the DementiaBank Pitt Corpus: A Statistical and Machine Learning Study Authors: Artsvik Avetisyan, Sachin Kumar Published: 2026-02-11 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.11028v1 Background: Subtle changes in spontaneous language production are among the earliest indicators of cognitive decline. Identifying linguistically interpretable markers of dementia can support transparent and clinically grounded screening approaches. Methods: This study analyzes spontaneous speech transcripts from the DementiaBank Pitt Corpus using three linguistic representations: raw cleaned text, a part-of-speech (POS)-enhanced representation combining lexical and grammatical information, and a POS-only syntactic representation. Logistic regression and random forest models were evaluated under two protocols: transcript-level train-test splits and subject-level five-fold cross-validation to prevent speaker overlap. Model interpretability was examined using global feature importance, and statistical validation was conducted using Mann-Whitney U tests with Cliff's delta effect sizes. Results: Across representations, models achieved stable performance, with syntactic and grammatical features retaining strong discriminative power even in the absence of lexical content. Subject-level evaluation yielded more conservative but consistent results, particularly for POS-enhanced and POS-only representations. Statistical analysis revealed significant group differences in functional word usage, lexical diversity, sentence structure, and discourse coherence, aligning closely with machine learning feature importance findings. Conclusion: The results demonstrate that abstract linguistic features capture robust markers of early cognitive decline under clinically realistic evaluation. By combining interpretable machine learning with non-parametric statistical validation, this study supports the use of linguistically grounded features for transparent and reliable language-based cognitive screening. --- ### Chain-of-Look Spatial Reasoning for Dense Surgical Instrument Counting Authors: Rishikesh Bhyri, Brian R Quaranto, Philip J Seger, Kaity Tung, Brendan Fox, Gene Yang, Steven D. Schwaitzberg, Junsong Yuan, Nan Xi, Peter C W Kim Published: 2026-02-11 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.11024v1 Accurate counting of surgical instruments in Operating Rooms (OR) is a critical prerequisite for ensuring patient safety during surgery. Despite recent progress of large visual-language models and agentic AI, accurately counting such instruments remains highly challenging, particularly in dense scenarios where instruments are tightly clustered. To address this problem, we introduce Chain-of-Look, a novel visual reasoning framework that mimics the sequential human counting process by enforcing a structured visual chain, rather than relying on classic object detection which is unordered. This visual chain guides the model to count along a coherent spatial trajectory, improving accuracy in complex scenes. To further enforce the physical plausibility of the visual chain, we introduce the neighboring loss function, which explicitly models the spatial constraints inherent to densely packed surgical instruments. We also present SurgCount-HD, a new dataset comprising 1,464 high-density surgical instrument images. Extensive experiments demonstrate that our method outperforms state-of-the-art approaches for counting (e.g., CountGD, REC) as well as Multimodality Large Language Models (e.g., Qwen, ChatGPT) in the challenging task of dense surgical instrument counting. --- ### ContactGaussian-WM: Learning Physics-Grounded World Model from Videos Authors: Meizhong Wang, Wanxin Jin, Kun Cao, Lihua Xie, Yiguang Hong Published: 2026-02-11 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2602.11021v1 Developing world models that understand complex physical interactions is essential for advancing robotic planning and simulation.However, existing methods often struggle to accurately model the environment under conditions of data scarcity and complex contact-rich dynamic motion.To address these challenges, we propose ContactGaussian-WM, a differentiable physics-grounded rigid-body world model capable of learning intricate physical laws directly from sparse and contact-rich video sequences.Our framework consists of two core components: (1) a unified Gaussian representation for both visual appearance and collision geometry, and (2) an end-to-end differentiable learning framework that differentiates through a closed-form physics engine to infer physical properties from sparse visual observations.Extensive simulations and real-world evaluations demonstrate that ContactGaussian-WM outperforms state-of-the-art methods in learning complex scenarios, exhibiting robust generalization capabilities.Furthermore, we showcase the practical utility of our framework in downstream applications, including data synthesis and real-time MPC. --- ### When Fusion Helps and When It Breaks: View-Aligned Robustness in Same-Source Financial Imaging Authors: Rui Ma Published: 2026-02-11 Categories: cs.LG, q-fin.ST arXiv: https://arxiv.org/abs/2602.11020v2 We study same-source multi-view learning and adversarial robustness for next-day direction prediction using two deterministic, window-aligned image views derived from the same time series: an OHLCV-rendered chart (ohlcv) and a technical-indicator matrix (indic). To control label ambiguity from near-zero moves, we use an ex-post minimum-movement threshold min_move (tau) based on realized absolute next-day return, defining an offline benchmark on the subset where the absolute next-day return is at least tau. Under leakage-resistant time-block splits with embargo, we compare early fusion (channel stacking) and dual-encoder late fusion with optional cross-branch consistency. We then evaluate pixel-space L-infinity evasion attacks (FGSM/PGD) under view-constrained and joint threat models. We find that fusion is regime dependent: early fusion can suffer negative transfer under noisier settings, whereas late fusion is a more reliable default once labels stabilize. Robustness degrades sharply under tiny budgets with stable view-dependent vulnerabilities; late fusion often helps under view-constrained attacks, but joint perturbations remain challenging. --- ### OSIL: Learning Offline Safe Imitation Policies with Safety Inferred from Non-preferred Trajectories Authors: Returaj Burnwal, Nirav Pravinbhai Bhatt, Balaraman Ravindran Published: 2026-02-11 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2602.11018v1 This work addresses the problem of offline safe imitation learning (IL), where the goal is to learn safe and reward-maximizing policies from demonstrations that do not have per-timestep safety cost or reward information. In many real-world domains, online learning in the environment can be risky, and specifying accurate safety costs can be difficult. However, it is often feasible to collect trajectories that reflect undesirable or unsafe behavior, implicitly conveying what the agent should avoid. We refer to these as non-preferred trajectories. We propose a novel offline safe IL algorithm, OSIL, that infers safety from non-preferred demonstrations. We formulate safe policy learning as a Constrained Markov Decision Process (CMDP). Instead of relying on explicit safety cost and reward annotations, OSIL reformulates the CMDP problem by deriving a lower bound on reward maximizing objective and learning a cost model that estimates the likelihood of non-preferred behavior. Our approach allows agents to learn safe and reward-maximizing behavior entirely from offline demonstrations. We empirically demonstrate that our approach can learn safer policies that satisfy cost constraints without degrading the reward performance, thus outperforming several baselines. --- ### From Buffers to Registers: Unlocking Fine-Grained FlashAttention with Hybrid-Bonded 3D NPU Co-Design Authors: Jinxin Yu, Yudong Pan, Mengdi Wang, Huawei Li, Yinhe Han, Xiaowei Li, Ying Wang Published: 2026-02-11 Categories: cs.AR, cs.AI arXiv: https://arxiv.org/abs/2602.11016v1 Transformer-based models dominate modern AI workloads but exacerbate memory bottlenecks due to their quadratic attention complexity and ever-growing model sizes. Existing accelerators, such as Groq and Cerebras, mitigate off-chip traffic with large on-chip caches, while algorithmic innovations such as FlashAttention fuse operators to avoid materializing large attention matrices. However, as off-chip traffic decreases, our measurements show that on-chip SRAM accesses account for over 60% of energy in long-sequence workloads, making cache access the new bottleneck. We propose 3D-Flow, a hybrid-bonded, 3D-stacked spatial accelerator that enables register-to-register communication across vertically partitioned PE tiers. Unlike 2D multi-array architectures limited by NoC-based router-to-router transfers, 3D-Flow leverages sub-10 um vertical TSVs to sustain cycle-level operator pipelining with minimal overhead. On top of this architecture, we design 3D-FlashAttention, a fine-grained scheduling method that balances latency across tiers, forming a bubble-free vertical dataflow without on-chip SRAM roundtrips. Evaluations on Transformer workloads (OPT and QWEN models) show that our 3D spatial accelerator reduces 46-93% energy consumption and achieves 1.4x-7.6x speedups compared to state-of-the-art 2D and 3D designs. --- ### CVPL: A Geometric Framework for Post-Hoc Linkage Risk Assessment in Protected Tabular Data Authors: Valery Khvatov, Alexey Neyman Published: 2026-02-11 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.11015v1 Formal privacy metrics provide compliance-oriented guarantees but often fail to quantify actual linkability in released datasets. We introduce CVPL (Cluster-Vector-Projection Linkage), a geometric framework for post-hoc assessment of linkage risk between original and protected tabular data. CVPL represents linkage analysis as an operator pipeline comprising blocking, vectorization, latent projection, and similarity evaluation, yielding continuous, scenario-dependent risk estimates rather than binary compliance verdicts. We formally define CVPL under an explicit threat model and introduce threshold-aware risk surfaces, R(lambda, tau), that capture the joint effects of protection strength and attacker strictness. We establish a progressive blocking strategy with monotonicity guarantees, enabling anytime risk estimation with valid lower bounds. We demonstrate that the classical Fellegi-Sunter linkage emerges as a special case of CVPL under restrictive assumptions, and that violations of these assumptions can lead to systematic over-linking bias. Empirical validation on 10,000 records across 19 protection configurations demonstrates that formal k-anonymity compliance may coexist with substantial empirical linkability, with a significant portion arising from non-quasi-identifier behavioral patterns. CVPL provides interpretable diagnostics identifying which features drive linkage feasibility, supporting privacy impact assessment, protection mechanism comparison, and utility-risk trade-off analysis. --- ### ROCKET: Rapid Optimization via Calibration-guided Knapsack Enhanced Truncation for Efficient Model Compression Authors: Ammar Ali, Baher Mohammad, Denis Makhov, Dmitriy Shopkhoev, Magauiya Zhussip, Stamatios Lefkimmiatis Published: 2026-02-11 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.11008v1 We present ROCKET, a training-free model compression method that achieves state-of-the-art performance in comparison with factorization, structured-sparsification and dynamic compression baselines. Operating under a global compression budget, ROCKET comprises two key innovations: First, it formulates layer-wise compression allocation as a multi-choice knapsack problem, selecting the optimal compression level for each layer to minimize total reconstruction error while adhering to a target model size. Second, it introduces a single-step sparse matrix factorization inspired by dictionary learning: using only a small calibration set, it sparsifies weight coefficients based on activation-weights sensitivity and then updates the dictionary in closed form via least squares bypassing iterative optimization, sparse coding, or backpropagation entirely. ROCKET consistently outperforms existing compression approaches across different model architectures at 20-50\% compression rates. Notably, it retains over 90\% of the original model's performance at 30\% compression without any fine-tuning. Moreover, when applying a light fine-tuning phase, recovery is substantially enhanced: for instance, compressing Qwen3-14B to an 8B-parameter model and healing it with just 30 million tokens yields performance nearly on par with the original Qwen3-8B. The code for ROCKET is at github.com/mts-ai/ROCKET/tree/main. --- ### LaSSM: Efficient Semantic-Spatial Query Decoding via Local Aggregation and State Space Models for 3D Instance Segmentation Authors: Lei Yao, Yi Wang, Yawen Cui, Moyun Liu, Lap-Pui Chau Published: 2026-02-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.11007v1 Query-based 3D scene instance segmentation from point clouds has attained notable performance. However, existing methods suffer from the query initialization dilemma due to the sparse nature of point clouds and rely on computationally intensive attention mechanisms in query decoders. We accordingly introduce LaSSM, prioritizing simplicity and efficiency while maintaining competitive performance. Specifically, we propose a hierarchical semantic-spatial query initializer to derive the query set from superpoints by considering both semantic cues and spatial distribution, achieving comprehensive scene coverage and accelerated convergence. We further present a coordinate-guided state space model (SSM) decoder that progressively refines queries. The novel decoder features a local aggregation scheme that restricts the model to focus on geometrically coherent regions and a spatial dual-path SSM block to capture underlying dependencies within the query set by integrating associated coordinates information. Our design enables efficient instance prediction, avoiding the incorporation of noisy information and reducing redundant computation. LaSSM ranks first place on the latest ScanNet++ V2 leaderboard, outperforming the previous best method by 2.5% mAP with only 1/3 FLOPs, demonstrating its superiority in challenging large-scale scene instance segmentation. LaSSM also achieves competitive performance on ScanNet, ScanNet200, S3DIS and ScanNet++ V1 benchmarks with less computational cost. Extensive ablation studies and qualitative results validate the effectiveness of our design. The code and weights are available at https://github.com/RayYoh/LaSSM. --- ### Interpretable Vision Transformers in Monocular Depth Estimation via SVDA Authors: Vasileios Arampatzakis, George Pavlidis, Nikolaos Mitianoudis, Nikos Papamarkos Published: 2026-02-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.11005v1 Monocular depth estimation is a central problem in computer vision with applications in robotics, AR, and autonomous driving, yet the self-attention mechanisms that drive modern Transformer architectures remain opaque. We introduce SVD-Inspired Attention (SVDA) into the Dense Prediction Transformer (DPT), providing the first spectrally structured formulation of attention for dense prediction tasks. SVDA decouples directional alignment from spectral modulation by embedding a learnable diagonal matrix into normalized query-key interactions, enabling attention maps that are intrinsically interpretable rather than post-hoc approximations. Experiments on KITTI and NYU-v2 show that SVDA preserves or slightly improves predictive accuracy while adding only minor computational overhead. More importantly, SVDA unlocks six spectral indicators that quantify entropy, rank, sparsity, alignment, selectivity, and robustness. These reveal consistent cross-dataset and depth-wise patterns in how attention organizes during training, insights that remain inaccessible in standard Transformers. By shifting the role of attention from opaque mechanism to quantifiable descriptor, SVDA redefines interpretability in monocular depth estimation and opens a principled avenue toward transparent dense prediction models. --- ### Enhancing Predictability of Multi-Tenant DNN Inference for Autonomous Vehicles' Perception Authors: Liangkai Liu, Kang G. Shin, Jinkyu Lee, Chengmo Yang, Weisong Shi Published: 2026-02-11 Categories: cs.CV, cs.AI, cs.RO, eess.SY arXiv: https://arxiv.org/abs/2602.11004v1 Autonomous vehicles (AVs) rely on sensors and deep neural networks (DNNs) to perceive their surrounding environment and make maneuver decisions in real time. However, achieving real-time DNN inference in the AV's perception pipeline is challenging due to the large gap between the computation requirement and the AV's limited resources. Most, if not all, of existing studies focus on optimizing the DNN inference time to achieve faster perception by compressing the DNN model with pruning and quantization. In contrast, we present a Predictable Perception system with DNNs (PP-DNN) that reduce the amount of image data to be processed while maintaining the same level of accuracy for multi-tenant DNNs by dynamically selecting critical frames and regions of interest (ROIs). PP-DNN is based on our key insight that critical frames and ROIs for AVs vary with the AV's surrounding environment. However, it is challenging to identify and use critical frames and ROIs in multi-tenant DNNs for predictable inference. Given image-frame streams, PP-DNN leverages an ROI generator to identify critical frames and ROIs based on the similarities of consecutive frames and traffic scenarios. PP-DNN then leverages a FLOPs predictor to predict multiply-accumulate operations (MACs) from the dynamic critical frames and ROIs. The ROI scheduler coordinates the processing of critical frames and ROIs with multiple DNN models. Finally, we design a detection predictor for the perception of non-critical frames. We have implemented PP-DNN in an ROS-based AV pipeline and evaluated it with the BDD100K and the nuScenes dataset. PP-DNN is observed to significantly enhance perception predictability, increasing the number of fusion frames by up to 7.3x, reducing the fusion delay by >2.6x and fusion-delay variations by >2.3x, improving detection completeness by 75.4% and the cost-effectiveness by up to 98% over the baseline. --- ### Fine-Tuning GPT-5 for GPU Kernel Generation Authors: Ali Tehrani, Yahya Emara, Essam Wissam, Wojciech Paluch, Waleed Atallah, Łukasz Dudziak, Mohamed S. Abdelfattah Published: 2026-02-11 Categories: cs.DC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.11000v1 Developing efficient GPU kernels is essential for scaling modern AI systems, yet it remains a complex task due to intricate hardware architectures and the need for specialized optimization expertise. Although Large Language Models (LLMs) demonstrate strong capabilities in general sequential code generation, they face significant challenges in GPU code generation because of the scarcity of high-quality labeled training data, compiler biases when generating synthetic solutions, and limited generalization across hardware generations. This precludes supervised fine-tuning (SFT) as a scalable methodology for improving current LLMs. In contrast, reinforcement learning (RL) offers a data-efficient and adaptive alternative but requires access to relevant tools, careful selection of training problems, and a robust evaluation environment. We present Makora's environment and tools for reinforcement learning finetuning of frontier models and report our results from fine-tuning GPT-5 for Triton code generation. In the single-attempt setting, our fine-tuned model improves kernel correctness from 43.7% to 77.0% (+33.3 percentage points) and increases the fraction of problems outperforming TorchInductor from 14.8% to 21.8% (+7 percentage points) compared to baseline GPT-5, while exceeding prior state-of-the-art models on KernelBench. When integrated into a full coding agent, it is able to solve up to 97.4% of problems in an expanded KernelBench suite, outperforming the PyTorch TorchInductor compiler on 72.9% of problems with a geometric mean speedup of 2.12x. Our work demonstrates that targeted post-training with reinforcement learning can unlock LLM capabilities in highly specialized technical domains where traditional supervised learning is limited by data availability, opening new pathways for AI-assisted accelerator programming. --- ### CLI-Gym: Scalable CLI Task Generation via Agentic Environment Inversion Authors: Yusong Lin, Haiyang Wang, Shuzhe Wu, Lue Fan, Feiyang Pan, Sanyuan Zhao, Dandan Tu Published: 2026-02-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.10999v1 Agentic coding requires agents to effectively interact with runtime environments, e.g., command line interfaces (CLI), so as to complete tasks like resolving dependency issues, fixing system problems, etc. But it remains underexplored how such environment-intensive tasks can be obtained at scale to enhance agents' capabilities. To address this, based on an analogy between the Dockerfile and the agentic task, we propose to employ agents to simulate and explore environment histories, guided by execution feedback. By tracing histories of a healthy environment, its state can be inverted to an earlier one with runtime failures, from which a task can be derived by packing the buggy state and the corresponding error messages. With our method, named CLI-Gym, a total of 1,655 environment-intensive tasks are derived, being the largest collection of its kind. Moreover, with curated successful trajectories, our fine-tuned model, named LiberCoder, achieves substantial absolute improvements of +21.1% (to 46.1%) on Terminal-Bench, outperforming various strong baselines. To our knowledge, this is the first public pipeline for scalable derivation of environment-intensive tasks. --- ### The emergence of numerical representations in communicating artificial agents Authors: Daniela Mihai, Lucas Weber, Francesca Franzon Published: 2026-02-11 Categories: cs.MA, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.10996v1 Human languages provide efficient systems for expressing numerosities, but whether the sheer pressure to communicate is enough for numerical representations to arise in artificial agents, and whether the emergent codes resemble human numerals at all, remains an open question. We study two neural network-based agents that must communicate numerosities in a referential game using either discrete tokens or continuous sketches, thus exploring both symbolic and iconic representations. Without any pre-defined numeric concepts, the agents achieve high in-distribution communication accuracy in both communication channels and converge on high-precision symbol-meaning mappings. However, the emergent code is non-compositional: the agents fail to derive systematic messages for unseen numerosities, typically reusing the symbol of the highest trained numerosity (discrete), or collapsing extrapolated values onto a single sketch (continuous). We conclude that the communication pressure alone suffices for precise transmission of learned numerosities, but additional pressures are needed to yield compositional codes and generalisation abilities. --- ### Interpretable Vision Transformers in Image Classification via SVDA Authors: Vasileios Arampatzakis, George Pavlidis, Nikolaos Mitianoudis, Nikos Papamarkos Published: 2026-02-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.10994v1 Vision Transformers (ViTs) have achieved state-of-the-art performance in image classification, yet their attention mechanisms often remain opaque and exhibit dense, non-structured behaviors. In this work, we adapt our previously proposed SVD-Inspired Attention (SVDA) mechanism to the ViT architecture, introducing a geometrically grounded formulation that enhances interpretability, sparsity, and spectral structure. We apply the use of interpretability indicators -- originally proposed with SVDA -- to monitor attention dynamics during training and assess structural properties of the learned representations. Experimental evaluations on four widely used benchmarks -- CIFAR-10, FashionMNIST, CIFAR-100, and ImageNet-100 -- demonstrate that SVDA consistently yields more interpretable attention patterns without sacrificing classification accuracy. While the current framework offers descriptive insights rather than prescriptive guidance, our results establish SVDA as a comprehensive and informative tool for analyzing and developing structured attention models in computer vision. This work lays the foundation for future advances in explainable AI, spectral diagnostics, and attention-based model compression. --- ### LoRA-Squeeze: Simple and Effective Post-Tuning and In-Tuning Compression of LoRA Modules Authors: Ivan Vulić, Adam Grycner, Quentin de Laroussilhe, Jonas Pfeiffer Published: 2026-02-11 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.10993v2 Despite its huge number of variants, standard Low-Rank Adaptation (LoRA) is still a dominant technique for parameter-efficient fine-tuning (PEFT). Nonetheless, it faces persistent challenges, including the pre-selection of an optimal rank and rank-specific hyper-parameters, as well as the deployment complexity of heterogeneous-rank modules and more sophisticated LoRA derivatives. In this work, we introduce LoRA-Squeeze, a simple and efficient methodology that aims to improve standard LoRA learning by changing LoRA module ranks either post-hoc or dynamically during training}. Our approach posits that it is better to first learn an expressive, higher-rank solution and then compress it, rather than learning a constrained, low-rank solution directly. The method involves fine-tuning with a deliberately high(er) source rank, reconstructing or efficiently approximating the reconstruction of the full weight update matrix, and then using Randomized Singular Value Decomposition (RSVD) to create a new, compressed LoRA module at a lower target rank. Extensive experiments across 13 text and 10 vision-language tasks show that post-hoc compression often produces lower-rank adapters that outperform those trained directly at the target rank, especially if a small number of fine-tuning steps at the target rank is allowed. Moreover, a gradual, in-tuning rank annealing variant of LoRA-Squeeze consistently achieves the best LoRA size-performance trade-off. --- ### Variational Optimality of Föllmer Processes in Generative Diffusions Authors: Yifan Chen, Eric Vanden-Eijnden Published: 2026-02-11 Categories: math.ST, cs.IT, cs.LG, math.PR, stat.ML arXiv: https://arxiv.org/abs/2602.10989v3 We construct and analyze generative diffusions that transport a point mass to a prescribed target distribution over a finite time horizon using the stochastic interpolant framework. The drift is expressed as a conditional expectation that can be estimated from independent samples without simulating stochastic processes. We show that the diffusion coefficient can be tuned \emph{a~posteriori} without changing the time-marginal distributions. Among all such tunings, we prove that minimizing the impact of estimation error on the path-space Kullback--Leibler divergence selects, in closed form, a Föllmer process -- a diffusion whose path measure minimizes relative entropy with respect to a reference process determined by the interpolation schedules alone. This yields a new variational characterization of Föllmer processes, complementing classical formulations via Schrödinger bridges and stochastic control, and provides a conditional-expectation representation of the Föllmer drift that enables simulation-free estimation from data. We further establish that, under this optimal diffusion coefficient, the path-space Kullback--Leibler divergence becomes independent of the interpolation schedule, rendering different schedules statistically equivalent in this variational sense. We provide numerical experiments to illustrate the impact of path-space variational optimality of Föllmer's processes in probabilistic forecasting and data assimilation applications. --- ### TVCACHE: A Stateful Tool-Value Cache for Post-Training LLM Agents Authors: Abhishek Vijaya Kumar, Bhaskar Kataria, Byungsoo Oh, Emaad Manzoor, Rachee Singh Published: 2026-02-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.10986v1 In RL post-training of LLM agents, calls to external tools take several seconds or even minutes, leaving allocated GPUs idle and inflating post-training time and cost. While many tool invocations repeat across parallel rollouts and could in principle be cached, naively caching their outputs for reuse is incorrect since tool outputs depend on the environment state induced by prior agent interactions. We present TVCACHE, a stateful tool-value cache for LLM agent post-training. TVCACHE maintains a tree of observed tool-call sequences and performs longest-prefix matching for cache lookups: a hit occurs only when the agent's full tool history matches a previously executed sequence, guaranteeing identical environment state. On three diverse workloads-terminal-based tasks, SQL generation, and video understanding. TVCACHE achieves cache hit rates of up to 70% and reduces median tool call execution time by up to 6.9X, with no degradation in post-training reward accumulation. --- ### DFIC: Towards a balanced facial image dataset for automatic ICAO compliance verification Authors: Nuno Gonçalves, Diogo Nunes, Carla Guerra, João Marcos Published: 2026-02-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.10985v1 Ensuring compliance with ISO/IEC and ICAO standards for facial images in machine-readable travel documents (MRTDs) is essential for reliable identity verification, but current manual inspection methods are inefficient in high-demand environments. This paper introduces the DFIC dataset, a novel comprehensive facial image dataset comprising around 58,000 annotated images and 2706 videos of more than 1000 subjects, that cover a broad range of non-compliant conditions, in addition to compliant portraits. Our dataset provides a more balanced demographic distribution than the existing public datasets, with one partition that is nearly uniformly distributed, facilitating the development of automated ICAO compliance verification methods. Using DFIC, we fine-tuned a novel method that heavily relies on spatial attention mechanisms for the automatic validation of ICAO compliance requirements, and we have compared it with the state-of-the-art aimed at ICAO compliance verification, demonstrating improved results. DFIC dataset is now made public (https://github.com/visteam-isr-uc/DFIC) for the training and validation of new models, offering an unprecedented diversity of faces, that will improve both robustness and adaptability to the intrinsically diverse combinations of faces and props that can be presented to the validation system. These results emphasize the potential of DFIC to enhance automated ICAO compliance methods but it can also be used in many other applications that aim to improve the security, privacy, and fairness of facial recognition systems. --- ### Sample Efficient Generative Molecular Optimization with Joint Self-Improvement Authors: Serra Korkmaz, Adam Izdebski, Jonathan Pirnay, Rasmus Møller-Larsen, Michal Kmicikiewicz, Pankhil Gawade, Dominik G. Grimm, Ewa Szczurek Published: 2026-02-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.10984v1 Generative molecular optimization aims to design molecules with properties surpassing those of existing compounds. However, such candidates are rare and expensive to evaluate, yielding sample efficiency essential. Additionally, surrogate models introduced to predict molecule evaluations, suffer from distribution shift as optimization drives candidates increasingly out-of-distribution. To address these challenges, we introduce Joint Self-Improvement, which benefits from (i) a joint generative-predictive model and (ii) a self-improving sampling scheme. The former aligns the generator with the surrogate, alleviating distribution shift, while the latter biases the generative part of the joint model using the predictive one to efficiently generate optimized molecules at inference-time. Experiments across offline and online molecular optimization benchmarks demonstrate that Joint Self-Improvement outperforms state-of-the-art methods under limited evaluation budgets. --- ### RiemannGL: Riemannian Geometry Changes Graph Deep Learning Authors: Li Sun, Qiqi Wan, Suyang Zhou, Zhenhao Huang, Philip S. Yu Published: 2026-02-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.10982v1 Graphs are ubiquitous, and learning on graphs has become a cornerstone in artificial intelligence and data mining communities. Unlike pixel grids in images or sequential structures in language, graphs exhibit a typical non-Euclidean structure with complex interactions among the objects. This paper argues that Riemannian geometry provides a principled and necessary foundation for graph representation learning, and that Riemannian graph learning should be viewed as a unifying paradigm rather than a collection of isolated techniques. While recent studies have explored the integration of graph learning and Riemannian geometry, most existing approaches are limited to a narrow class of manifolds, particularly hyperbolic spaces, and often adopt extrinsic manifold formulations. We contend that the central mission of Riemannian graph learning is to endow graph neural networks with intrinsic manifold structures, which remains underexplored. To advance this perspective, we identify key conceptual and methodological gaps in existing approaches and outline a structured research agenda along three dimensions: manifold type, neural architecture, and learning paradigm. We further discuss open challenges, theoretical foundations, and promising directions that are critical for unlocking the full potential of Riemannian graph learning. This paper aims to provide a coherent viewpoint and to stimulate broader exploration of Riemannian geometry as a foundational framework for future graph learning research. --- ### VFGS-Net: Frequency-Guided State-Space Learning for Topology-Preserving Retinal Vessel Segmentation Authors: Ruiqi Song, Lei Liu, Ya-Nan Zhang, Chao Wang, Xiaoning Li, Nan Mu Published: 2026-02-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.10978v1 Accurate retinal vessel segmentation is a critical prerequisite for quantitative analysis of retinal images and computer-aided diagnosis of vascular diseases such as diabetic retinopathy. However, the elongated morphology, wide scale variation, and low contrast of retinal vessels pose significant challenges for existing methods, making it difficult to simultaneously preserve fine capillaries and maintain global topological continuity. To address these challenges, we propose the Vessel-aware Frequency-domain and Global Spatial modeling Network (VFGS-Net), an end-to-end segmentation framework that seamlessly integrates frequency-aware feature enhancement, dual-path convolutional representation learning, and bidirectional asymmetric spatial state-space modeling within a unified architecture. Specifically, VFGS-Net employs a dual-path feature convolution module to jointly capture fine-grained local textures and multi-scale contextual semantics. A novel vessel-aware frequency-domain channel attention mechanism is introduced to adaptively reweight spectral components, thereby enhancing vessel-relevant responses in high-level features. Furthermore, at the network bottleneck, we propose a bidirectional asymmetric Mamba2-based spatial modeling block to efficiently capture long-range spatial dependencies and strengthen the global continuity of vascular structures. Extensive experiments on four publicly available retinal vessel datasets demonstrate that VFGS-Net achieves competitive or superior performance compared to state-of-the-art methods. Notably, our model consistently improves segmentation accuracy for fine vessels, complex branching patterns, and low-contrast regions, highlighting its robustness and clinical potential. --- ### FeatureBench: Benchmarking Agentic Coding for Complex Feature Development Authors: Qixing Zhou, Jiacheng Zhang, Haiyang Wang, Rui Hao, Jiahe Wang, Minghao Han, Yuxue Yang, Shuzhe Wu, Feiyang Pan, Lue Fan, Dandan Tu, Zhaoxiang Zhang Published: 2026-02-11 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2602.10975v1 Agents powered by large language models (LLMs) are increasingly adopted in the software industry, contributing code as collaborators or even autonomous developers. As their presence grows, it becomes important to assess the current boundaries of their coding abilities. Existing agentic coding benchmarks, however, cover a limited task scope, e.g., bug fixing within a single pull request (PR), and often rely on non-executable evaluations or lack an automated approach for continually updating the evaluation coverage. To address such issues, we propose FeatureBench, a benchmark designed to evaluate agentic coding performance in end-to-end, feature-oriented software development. FeatureBench incorporates an execution-based evaluation protocol and a scalable test-driven method that automatically derives tasks from code repositories with minimal human effort. By tracing from unit tests along a dependency graph, our approach can identify feature-level coding tasks spanning multiple commits and PRs scattered across the development timeline, while ensuring the proper functioning of other features after the separation. Using this framework, we curated 200 challenging evaluation tasks and 3825 executable environments from 24 open-source repositories in the first version of our benchmark. Empirical evaluation reveals that the state-of-the-art agentic model, such as Claude 4.5 Opus, which achieves a 74.4% resolved rate on SWE-bench, succeeds on only 11.0% of tasks, opening new opportunities for advancing agentic coding. Moreover, benefiting from our automated task collection toolkit, FeatureBench can be easily scaled and updated over time to mitigate data leakage. The inherent verifiability of constructed environments also makes our method potentially valuable for agent training. --- ### A Jointly Efficient and Optimal Algorithm for Heteroskedastic Generalized Linear Bandits with Adversarial Corruptions Authors: Sanghwa Kim, Junghyun Lee, Se-Young Yun Published: 2026-02-11 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2602.10971v2 We consider the problem of heteroskedastic generalized linear bandits (GLBs) with adversarial corruptions, which subsumes heteroskedastic linear bandits and logistic/Poisson bandits, in the presence of adversarial corruptions. We propose HCW-GLB-OMD, which consists of two components: an online mirror descent (OMD)-based estimator and Hessian-based confidence weights to achieve corruption robustness. This is computationally efficient in that it only requires ${O}(1)$ space and time complexity per iteration. Under the self-concordance assumption on the link function, we show a regret bound of $\tilde{O}\left( d \sqrt{\sum_t g(τ_t) \dotμ_{t,\star}} + d^2 g_{\max} κ+ d (g_{\max} + κ) C \right)$, where $\dotμ_{t,\star}$ is the slope of $μ$ around the optimal arm at time $t$, $g(τ_t)$'s are potentially exogenously time-varying dispersions (e.g., $g(τ_t) = σ_t^2$ for heteroskedastic linear bandits, $g(τ_t) = 1$ for Bernoulli and Poisson), $g_{\max} = \max_{t \in (T)} g(τ_t)$ is the maximum dispersion, and $C \geq 0$ is the total corruption budget of the adversary. We complement this with a lower bound of $\tildeΩ(d \sqrt{\sum_t g(τ_t) \dotμ_{t,\star}} + d C)$, unifying previous problem-specific lower bounds. Thus, our algorithm achieves, up to a $κ$-factor in the corruption term, instance-wise minimax optimality simultaneously across various instances of heteroskedastic GLBs with adversarial corruptions. --- ### Weighting-Based Identification and Estimation in Graphical Models of Missing Data Authors: Anna Guo, Razieh Nabi Published: 2026-02-11 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2602.10969v1 We propose a constructive algorithm for identifying complete data distributions in graphical models of missing data. The complete data distribution is unrestricted, while the missingness mechanism is assumed to factorize according to a conditional directed acyclic graph. Our approach follows an interventionist perspective in which missingness indicators are treated as variables that can be intervened on. A central challenge in this setting is that sequences of interventions on missingness indicators may induce and propagate selection bias, so that identification can fail even when a propensity score is invariant to available interventions. To address this challenge, we introduce a tree-based identification algorithm that explicitly tracks the creation and propagation of selection bias and determines whether it can be avoided through admissible intervention strategies. The resulting tree provides both a diagnostic and a constructive characterization of identifiability under a given missingness mechanism. Building on these results, we develop recursive inverse probability weighting procedures that mirror the intervention logic of the identification algorithm, yielding valid estimating equations for both the missingness mechanism and functionals of the complete data distribution. Simulation studies and a real-data application illustrate the practical performance of the proposed methods. An accompanying R package, flexMissing, implements all proposed procedures. --- ### Healthy Harvests: A Comparative Look at Guava Disease Classification Using InceptionV3 Authors: Samanta Ghosh, Shaila Afroz Anika, Umma Habiba Ahmed, B. M. Shahria Alam, Mohammad Tahmid Noor, Nishat Tasnim Niloy Published: 2026-02-11 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.10967v1 Guava fruits often suffer from many diseases. This can harm fruit quality and fruit crop yield. Early identification is important for minimizing damage and ensuring fruit health. This study focuses on 3 different categories for classifying diseases. These are Anthracnose, Fruit flies, and Healthy fruit. The data set used in this study is collected from Mendeley Data. This dataset contains 473 original images of Guava. These images vary in size and format. The original dataset was resized to 256x256 pixels with RGB color mode for better consistency. After this, the Data augmentation process is applied to improve the dataset by generating variations of the original images. The augmented dataset consists of 3784 images using advanced preprocessing techniques. Two deep learning models were implemented to classify the images. The InceptionV3 model is well known for its advanced framework. These apply multiple convolutional filters for obtaining different features effectively. On the other hand, the ResNet50 model helps to train deeper networks by using residual learning. The InceptionV3 model achieved the impressive accuracy of 98.15%, and ResNet50got 94.46% accuracy. Data mixing methods such as CutMix and MixUp were applied to enhance the model's robustness. The confusion matrix was used to evaluate the overall model performance of both InceptionV3 and Resnet50. Additionally, SHAP analysis is used to improve interpretability, which helps to find the significant parts of the image for the model prediction. This study purposes to highlight how advanced models enhan --- ### MoEEdit: Efficient and Routing-Stable Knowledge Editing for Mixture-of-Experts LLMs Authors: Yupu Gu, Rongzhe Wei, Andy Zhu, Pan Li Published: 2026-02-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.10965v1 Knowledge editing (KE) enables precise modifications to factual content in large language models (LLMs). Existing KE methods are largely designed for dense architectures, limiting their applicability to the increasingly prevalent sparse Mixture-of-Experts (MoE) models that underpin modern scalable LLMs. Although MoEs offer strong efficiency and capacity scaling, naively adapting dense-model editors is both computationally costly and prone to routing distribution shifts that undermine stability and consistency. To address these challenges, we introduce MoEEdit, the first routing-stable framework for parameter-modifying knowledge editing in MoE LLMs. Our method reparameterizes expert updates via per-expert null-space projections that keep router inputs invariant and thereby suppress routing shifts. The resulting block-structured optimization is solved efficiently with a block coordinate descent (BCD) solver. Experiments show that MoEEdit attains state-of-the-art efficacy and generalization while preserving high specificity and routing stability, with superior compute and memory efficiency. These results establish a robust foundation for scalable, precise knowledge editing in sparse LLMs and underscore the importance of routing-stable interventions. --- ### Can LLMs Cook Jamaican Couscous? A Study of Cultural Novelty in Recipe Generation Authors: F. Carichon, R. Rampa, G. Farnadi Published: 2026-02-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.10964v1 Large Language Models (LLMs) are increasingly used to generate and shape cultural content, ranging from narrative writing to artistic production. While these models demonstrate impressive fluency and generative capacity, prior work has shown that they also exhibit systematic cultural biases, raising concerns about stereotyping, homogenization, and the erasure of culturally specific forms of expression. Understanding whether LLMs can meaningfully align with diverse cultures beyond the dominant ones remains a critical challenge. In this paper, we study cultural adaptation in LLMs through the lens of cooking recipes, a domain in which culture, tradition, and creativity are tightly intertwined. We build on the \textit{GlobalFusion} dataset, which pairs human recipes from different countries according to established measures of cultural distance. Using the same country pairs, we generate culturally adapted recipes with multiple LLMs, enabling a direct comparison between human and LLM behavior in cross-cultural content creation. Our analysis shows that LLMs fail to produce culturally representative adaptations. Unlike humans, the divergence of their generated recipes does not correlate with cultural distance. We further provide explanations for this gap. We show that cultural information is weakly preserved in internal model representations, that models inflate novelty in their production by misunderstanding notions such as creativity and tradition, and that they fail to identify adaptation with its associated countries and to ground it in culturally salient elements such as ingredients. These findings highlight fundamental limitations of current LLMs for culturally oriented generation and have important implications for their use in culturally sensitive applications. --- ### Rotary Positional Embeddings as Phase Modulation: Theoretical Bounds on the RoPE Base for Long-Context Transformers Authors: Feilong Liu Published: 2026-02-11 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.10959v1 Rotary positional embeddings (RoPE) are widely used in large language models to encode token positions through multiplicative rotations, yet their behavior at long context lengths remains poorly characterized. In this work, we reinterpret RoPE as phase modulation applied to a bank of complex oscillators, enabling analysis through classical signal processing theory. Under this formulation, we derive principled lower bounds on the RoPE base parameter that are necessary to preserve positional coherence over a target context length. These include a fundamental aliasing bound, analogous to a Nyquist limit, and a DC-component stability bound that constrains phase drift in low-frequency positional modes. We further extend this analysis to deep transformers, showing that repeated rotary modulation across layers compounds angular misalignment, tightening the base requirement as depth increases. Complementing these results, we derive a precision-dependent upper bound on the RoPE base arising from finite floating-point resolution. Beyond this limit, incremental phase updates become numerically indistinguishable, leading to positional erasure even in the absence of aliasing. Together, the lower and upper bounds define a precision- and depth-dependent feasibility region a Goldilocks zone for long-context transformers. We validate the framework through a comprehensive case study of state-of-the-art models, including LLaMA, Mistral, and DeepSeek variants, showing that observed successes, failures, and community retrofits align closely with the predicted bounds. Notably, models that violate the stability bound exhibit attention collapse and long-range degradation, while attempts to scale beyond one million tokens encounter a hard precision wall independent of architecture or training. --- ### Stochastic Parroting in Temporal Attention -- Regulating the Diagonal Sink Authors: Victoria Hankemeier, Malte Schilling Published: 2026-02-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.10956v3 Spatio-temporal models analyze spatial structures and temporal dynamics, which makes them prone to information degeneration among space and time. Prior literature has demonstrated that over-squashing in causal attention or temporal convolutions creates a bias on the first tokens. To analyze whether such a bias is present in temporal attention mechanisms, we derive sensitivity bounds on the expected value of the Jacobian of a temporal attention layer. We theoretically show how off-diagonal attention scores depend on the sequence length, and that temporal attention matrices suffer a diagonal attention sink. We suggest regularization methods, and experimentally demonstrate their effectiveness. --- ### Search or Accelerate: Confidence-Switched Position Beam Search for Diffusion Language Models Authors: Mingyu Cao, Alvaro H. C. Correia, Christos Louizos, Shiwei Liu, Lu Yin Published: 2026-02-11 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.10953v2 Diffusion Language Models (DLMs) generate text by iteratively denoising a masked sequence, repeatedly deciding which positions to commit at each step. Standard decoding follows a greedy rule: unmask the most confident positions, yet this local choice can lock the model into a suboptimal unmasking order, especially on reasoning-heavy prompts. We present SOAR, a training-free decoding algorithm that adapts its behavior to the model's uncertainty. When confidence is low, SOAR briefly widens the search over alternative unmasking decisions to avoid premature commitments; when confidence is high, it collapses the search and decodes many positions in parallel to reduce the number of denoising iterations. Across mathematical reasoning and code generation benchmarks (GSM8K, MBPP, HumanEval) on Dream-7B and LLaDA-8B, SOAR improves generation quality while maintaining competitive inference speed, offering a practical way to balance quality and efficiency in DLM decoding. Our Code is available at https://github.com/duterscmy/SOAR --- ### Optimal Initialization in Depth: Lyapunov Initialization and Limit Theorems for Deep Leaky ReLU Networks Authors: Constantin Kogler, Tassilo Schwarz, Samuel Kittle Published: 2026-02-11 Categories: stat.ML, cs.LG, math.DS, math.PR arXiv: https://arxiv.org/abs/2602.10949v2 Effective initialization in deep networks requires an understanding of random neural networks. In this work, a rigorous probabilistic analysis of deep bias-free random Leaky ReLU networks is provided. We prove a Law of Large Numbers and a Central Limit Theorem for the logarithm of the norm of network activations, establishing that, as the number of layers increases, their growth is governed by a parameter called the Lyapunov exponent. This parameter characterizes a sharp phase transition between vanishing and exploding activations, and we calculate the Lyapunov exponent explicitly for Gaussian or orthogonal weight matrices. Our results reveal that standard methods, such as He initialization or orthogonal initialization, do not guarantee activation stability for deep networks of low width. Based on these theoretical insights, we propose a novel initialization method, referred to as Lyapunov initialization, which sets the Lyapunov exponent to zero and thereby ensures that the neural network is as stable as possible, leading empirically to improved learning. --- ### Computational Phenomenology of Temporal Experience in Autism: Quantifying the Emotional and Narrative Characteristics of Lived Unpredictability Authors: Kacper Dudzic, Karolina Drożdż, Maciej Wodziński, Anastazja Szuła, Marcin Moskalewicz Published: 2026-02-11 Categories: cs.CL, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2602.10947v2 Disturbances in temporality, such as desynchronization with the social environment and its unpredictability, are considered core features of autism with a deep impact on relationships. However, limitations regarding research on this issue include: 1) the dominance of deficit-based medical models of autism, 2) sample size in qualitative research, and 3) the lack of phenomenological anchoring in computational research. To bridge the gap between phenomenological and computational approaches and overcome sample-size limitations, our research integrated three methodologies. Study A: structured phenomenological interviews with autistic individuals using the Transdiagnostic Assessment of Temporal Experience. Study B: computational analysis of an autobiographical corpus of autistic narratives built for this purpose. Study C: a replication of a computational study using narrative flow measures to assess the perceived phenomenological authenticity of autistic autobiographies. Interviews revealed that the most significant differences between the autistic and control groups concerned unpredictability of experience. Computational results mirrored these findings: the temporal lexicon in autistic narratives was significantly more negatively valenced - particularly the "Immediacy & Suddenness" category. Outlier analysis identified terms associated with perceived discontinuity (unpredictably, precipitously, and abruptly) as highly negative. The computational analysis of narrative flow found that the autistic narratives contained within the corpus quantifiably resemble autobiographical stories more than imaginary ones. Overall, the temporal challenges experienced by autistic individuals were shown to primarily concern lived unpredictability and stem from the contents of lived experience, and not from autistic narrative construction. --- ### Towards Learning a Generalizable 3D Scene Representation from 2D Observations Authors: Martin Gromniak, Jan-Gerrit Habekost, Sebastian Kamp, Sven Magg, Stefan Wermter Published: 2026-02-11 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2602.10943v1 We introduce a Generalizable Neural Radiance Field approach for predicting 3D workspace occupancy from egocentric robot observations. Unlike prior methods operating in camera-centric coordinates, our model constructs occupancy representations in a global workspace frame, making it directly applicable to robotic manipulation. The model integrates flexible source views and generalizes to unseen object arrangements without scene-specific finetuning. We demonstrate the approach on a humanoid robot and evaluate predicted geometry against 3D sensor ground truth. Trained on 40 real scenes, our model achieves 26mm reconstruction error, including occluded regions, validating its ability to infer complete 3D occupancy beyond traditional stereo vision methods. --- ### FastUSP: A Multi-Level Collaborative Acceleration Framework for Distributed Diffusion Model Inference Authors: Guandong Li Published: 2026-02-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.10940v1 Large-scale diffusion models such as FLUX (12B parameters) and Stable Diffusion 3 (8B parameters) require multi-GPU parallelism for efficient inference. Unified Sequence Parallelism (USP), which combines Ulysses and Ring attention mechanisms, has emerged as the state-of-the-art approach for distributed attention computation. However, existing USP implementations suffer from significant inefficiencies including excessive kernel launch overhead and suboptimal computation-communication scheduling. In this paper, we propose \textbf{FastUSP}, a multi-level optimization framework that integrates compile-level optimization (graph compilation with CUDA Graphs and computation-communication reordering), communication-level optimization (FP8 quantized collective communication), and operator-level optimization (pipelined Ring attention with double buffering). We evaluate FastUSP on FLUX (12B) and Qwen-Image models across 2, 4, and 8 NVIDIA RTX 5090 GPUs. On FLUX, FastUSP achieves consistent \textbf{1.12$\times$--1.16$\times$} end-to-end speedup over baseline USP, with compile-level optimization contributing the dominant improvement. On Qwen-Image, FastUSP achieves \textbf{1.09$\times$} speedup on 2 GPUs; on 4--8 GPUs, we identify a PyTorch Inductor compatibility limitation with Ring attention that prevents compile optimization, while baseline USP scales to 1.30$\times$--1.46$\times$ of 2-GPU performance. We further provide a detailed analysis of the performance characteristics of distributed diffusion inference, revealing that kernel launch overhead -- rather than communication latency -- is the primary bottleneck on modern high-bandwidth GPU interconnects. --- ### What do people want to fact-check? Authors: Bijean Ghafouri, Dorsaf Sallami, Luca Luceri, Taylor Lynn Curtis, Jean-Francois Godbout, Emilio Ferrara, Reihaneh Rabbany Published: 2026-02-11 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2602.10935v1 Research on misinformation has focused almost exclusively on supply, asking what falsehoods circulate, who produces them, and whether corrections work. A basic demand-side question remains unanswered. When ordinary people can fact-check anything they want, what do they actually ask about? We provide the first large-scale evidence on this question by analyzing close to 2{,}500 statements submitted by 457 participants to an open-ended AI fact-checking system. Each claim is classified along five semantic dimensions (domain, epistemic form, verifiability, target entity, and temporal reference), producing a behavioral map of public verification demand. Three findings stand out. First, users range widely across topics but default to a narrow epistemic repertoire, overwhelmingly submitting simple descriptive claims about present-day observables. Second, roughly one in four requests concerns statements that cannot be empirically resolved, including moral judgments, speculative predictions, and subjective evaluations, revealing a systematic mismatch between what users seek from fact-checking tools and what such tools can deliver. Third, comparison with the FEVER benchmark dataset exposes sharp structural divergences across all five dimensions, indicating that standard evaluation corpora encode a synthetic claim environment that does not resemble real-world verification needs. These results reframe fact-checking as a demand-driven problem and identify where current AI systems and benchmarks are misaligned with the uncertainty people actually experience. --- ### CMAD: Cooperative Multi-Agent Diffusion via Stochastic Optimal Control Authors: Riccardo Barbano, Alexander Denker, Zeljko Kereta, Runchang Li, Francisco Vargas Published: 2026-02-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.10933v2 Continuous-time generative models have achieved remarkable success in image restoration and synthesis. However, controlling the composition of multiple pre-trained models remains an open challenge. Current approaches largely treat composition as an algebraic composition of probability densities, such as via products or mixtures of experts. This perspective assumes the target distribution is known explicitly, which is almost never the case. In this work, we propose a different paradigm that formulates compositional generation as a cooperative Stochastic Optimal Control problem. Rather than combining probability densities, we treat pre-trained diffusion models as interacting agents whose diffusion trajectories are jointly steered, via optimal control, toward a shared objective defined on their aggregated output. We validate our framework on conditional MNIST generation and compare it against a naïve inference-time DPS-style baseline replacing learned cooperative control with per-step gradient guidance. --- ### Spatial-Morphological Modeling for Multi-Attribute Imputation of Urban Blocks Authors: Vasilii Starikov, Ruslan Kozliak, Georgii Kontsevik, Sergey Mityagin Published: 2026-02-11 Categories: cs.LG, cs.CY arXiv: https://arxiv.org/abs/2602.10923v1 Accurate reconstruction of missing morphological indicators of a city is crucial for urban planning and data-driven analysis. This study presents the spatial-morphological (SM) imputer tool, which combines data-driven morphological clustering with neighborhood-based methods to reconstruct missing values of the floor space index (FSI) and ground space index (GSI) at the city block level, inspired by the SpaceMatrix framework. This approach combines city-scale morphological patterns as global priors with local spatial information for context-dependent interpolation. The evaluation shows that while SM alone captures meaningful morphological structure, its combination with inverse distance weighting (IDW) or spatial k-nearest neighbor (sKNN) methods provides superior performance compared to existing SOTA models. Composite methods demonstrate the complementary advantages of combining morphological and spatial approaches. ---