# Research Papers — 2026-02 · bundle page 201 of 210 > Full-text markdown of papers #10001–10050 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/201 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/200.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/202.md) ### DIA-CLIP: a universal representation learning framework for zero-shot DIA proteomics Authors: Yucheng Liao, Han Wen, Weinan E, Weijie Zhang Published: 2026-02-02 Categories: cs.LG, cs.AI, q-bio.QM arXiv: https://arxiv.org/abs/2602.01772v1 Data-independent acquisition mass spectrometry (DIA-MS) has established itself as a cornerstone of proteomic profiling and large-scale systems biology, offering unparalleled depth and reproducibility. Current DIA analysis frameworks, however, require semi-supervised training within each run for peptide-spectrum match (PSM) re-scoring. This approach is prone to overfitting and lacks generalizability across diverse species and experimental conditions. Here, we present DIA-CLIP, a pre-trained model shifting the DIA analysis paradigm from semi-supervised training to universal cross-modal representation learning. By integrating dual-encoder contrastive learning framework with encoder-decoder architecture, DIA-CLIP establishes a unified cross-modal representation for peptides and corresponding spectral features, achieving high-precision, zero-shot PSM inference. Extensive evaluations across diverse benchmarks demonstrate that DIA-CLIP consistently outperforms state-of-the-art tools, yielding up to a 45% increase in protein identification while achieving a 12% reduction in entrapment identifications. Moreover, DIA-CLIP holds immense potential for diverse practical applications, such as single-cell and spatial proteomics, where its enhanced identification depth facilitates the discovery of novel biomarkers and the elucidates of intricate cellular mechanisms. --- ### <SOG_k>: One LLM Token for Explicit Graph Structural Understanding Authors: Jingyao Wu, Bin Lu, Zijun Di, Xiaoying Gan, Meng Jin, Luoyi Fu, Xinbing Wang, Chenghu Zhou Published: 2026-02-02 Categories: cs.CL, cs.AI, cs.NI arXiv: https://arxiv.org/abs/2602.01771v1 Large language models show great potential in unstructured data understanding, but still face significant challenges with graphs due to their structural hallucination. Existing approaches mainly either verbalize graphs into natural language, which leads to excessive token consumption and scattered attention, or transform graphs into trainable continuous embeddings (i.e., soft prompt), but exhibit severe misalignment with original text tokens. To solve this problem, we propose to incorporate one special token <SOG_k> to fully represent the Structure Of Graph within a unified token space, facilitating explicit topology input and structural information sharing. Specifically, we propose a topology-aware structural tokenizer that maps each graph topology into a highly selective single token. Afterwards, we construct a set of hybrid structure Question-Answering corpora to align new structural tokens with existing text tokens. With this approach, <SOG_k> empowers LLMs to understand, generate, and reason in a concise and accurate manner. Extensive experiments on five graph-level benchmarks demonstrate the superiority of our method, achieving a performance improvement of 9.9% to 41.4% compared to the baselines while exhibiting interpretability and consistency. Furthermore, our method provides a flexible extension to node-level tasks, enabling both global and local structural understanding. The codebase is publicly available at https://github.com/Jingyao-Wu/SOG. --- ### IRIS: Implicit Reward-Guided Internal Sifting for Mitigating Multimodal Hallucination Authors: Yuanshuai Li, Yuping Yan, Jirui Han, Fei Ming, Lingjuan Lv, Yaochu Jin Published: 2026-02-02 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.01769v2 Hallucination remains a fundamental challenge for Multimodal Large Language Models (MLLMs). While Direct Preference Optimization (DPO) is a key alignment framework, existing approaches often rely heavily on costly external evaluators for scoring or rewriting, incurring off-policy learnability gaps and discretization loss. Due to the lack of access to internal states, such feedback overlooks the fine-grained conflicts between different modalities that lead to hallucinations during generation. To address this issue, we propose IRIS (Implicit Reward-Guided Internal Sifting), which leverages continuous implicit rewards in the native log-probability space to preserve full information density and capture internal modal competition. This on-policy paradigm eliminates learnability gaps by utilizing self-generated preference pairs. By sifting these pairs based on multimodal implicit rewards, IRIS ensures that optimization is driven by signals that directly resolve modal conflicts. Extensive experiments demonstrate that IRIS achieves highly competitive performance on key hallucination benchmarks using only 5.7k samples, without requiring any external feedback during preference alignment. These results confirm that IRIS provides an efficient and principled paradigm for mitigating MLLM hallucinations. --- ### CoMeT: Collaborative Memory Transformer for Efficient Long Context Modeling Authors: Runsong Zhao, Shilei Liu, Jiwei Tang, Langming Liu, Haibin Chen, Weidong Zhang, Yujin Yuan, Tong Xiao, Jingbo Zhu, Wenbo Su, Bo Zheng Published: 2026-02-02 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.01766v2 The quadratic complexity and indefinitely growing key-value (KV) cache of standard Transformers pose a major barrier to long-context processing. To overcome this, we introduce the Collaborative Memory Transformer (CoMeT), a novel architecture that enables LLMs to handle arbitrarily long sequences with constant memory usage and linear time complexity. Designed as an efficient, plug-in module, CoMeT can be integrated into pre-trained models with only minimal fine-tuning. It operates on sequential data chunks, using a dual-memory system to manage context: a temporary memory on a FIFO queue for recent events, and a global memory with a gated update rule for long-range dependencies. These memories then act as a dynamic soft prompt for the next chunk. To enable efficient fine-tuning on extremely long contexts, we introduce a novel layer-level pipeline parallelism strategy. The effectiveness of our approach is remarkable: a model equipped with CoMeT and fine-tuned on 32k contexts can accurately retrieve a passkey from any position within a 1M token sequence. On the SCROLLS benchmark, CoMeT surpasses other efficient methods and achieves performance comparable to a full-attention baseline on summarization tasks. Its practical effectiveness is further validated on real-world agent and user behavior QA tasks. The code is available at: https://github.com/LivingFutureLab/Comet --- ### Backdoor Sentinel: Detecting and Detoxifying Backdoors in Diffusion Models via Temporal Noise Consistency Authors: Bingzheng Wang, Xiaoyan Gu, Hongbo Xu, Hongcheng Li, Zimo Yu, Jiang Zhou, Weiping Wang, Wu Liu Published: 2026-02-02 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.01765v2 Diffusion models have been widely deployed in AIGC services, but their reliance on opaque training data exposes them to backdoor attacks. In practical auditing scenarios, auditors are typically unable to access model parameters due to intellectual property protection, making white-box or query-intensive detection impractical. After detection, existing detoxification approaches are trapped in a dilemma between detoxification effectiveness and generation quality for service providers. We reveal Temporal Noise Consistency (TNC), a previously unreported phenomenon in which backdoor activation disrupts the consistency of noise predictions between adjacent diffusion timesteps within specific temporal segments, while clean inputs remain stable. Based on this finding, we propose TNC-Defense, a closed-loop framework for gray-box backdoor detection and model repair. Specifically, TNC-Detect (for auditors) uses inference-stage adjacent-noise statistics to detect backdoors and precisely localize anomalous timesteps without model-weight access. TNC-Detox (for service providers) utilizes these locations to perform trigger-agnostic, timestep-aware correction of the generation path, suppressing backdoor behavior while reducing detoxification cost. Across five representative backdoor attacks and state-of-the-art defenses, TNC-Defense improves the average detection accuracy by $11\%$ with negligible additional overhead, and invalidates an average of $98.5\%$ of triggered samples with only a mild degradation in generation quality. Our code is publicly available at: https://github.com/binzhwang/TNC-Defense. --- ### Backdoor Sentinel: Detecting and Detoxifying Backdoors in Diffusion Models via Temporal Noise Consistency Authors: Bingzheng Wang, Xiaoyan Gu, Hongbo Xu, Hongcheng Li, Zimo Yu, Jiang Zhou, Weiping Wang Published: 2026-02-02 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.01765v1 Diffusion models have been widely deployed in AIGC services; however, their reliance on opaque training data and procedures exposes a broad attack surface for backdoor injection. In practical auditing scenarios, due to the protection of intellectual property and commercial confidentiality, auditors are typically unable to access model parameters, rendering existing white-box or query-intensive detection methods impractical. More importantly, even after the backdoor is detected, existing detoxification approaches are often trapped in a dilemma between detoxification effectiveness and generation quality. In this work, we identify a previously unreported phenomenon called temporal noise unconsistency, where the noise predictions between adjacent diffusion timesteps is disrupted in specific temporal segments when the input is triggered, while remaining stable under clean inputs. Leveraging this finding, we propose Temporal Noise Consistency Defense (TNC-Defense), a unified framework for backdoor detection and detoxification. The framework first uses the adjacent timestep noise consistency to design a gray-box detection module, for identifying and locating anomalous diffusion timesteps. Furthermore, the framework uses the identified anomalous timesteps to construct a trigger-agnostic, timestep-aware detoxification module, which directly corrects the backdoor generation path. This effectively suppresses backdoor behavior while significantly reducing detoxification costs. We evaluate the proposed method under five representative backdoor attack scenarios and compare it with state-of-the-art defenses. The results show that TNC-Defense improves the average detection accuracy by $11\%$ with negligible additional overhead, and invalidates an average of $98.5\%$ of triggered samples with only a mild degradation in generation quality. --- ### GDPR-Compliant Person Recognition in Industrial Environments Using MEMS-LiDAR and Hybrid Data Authors: Dennis Basile, Dennis Sprute, Helene Dörksen, Holger Flatt Published: 2026-02-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.01764v1 The reliable detection of unauthorized individuals in safety-critical industrial indoor spaces is crucial to avoid plant shutdowns, property damage, and personal hazards. Conventional vision-based methods that use deep-learning approaches for person recognition provide image information but are sensitive to lighting and visibility conditions and often violate privacy regulations, such as the General Data Protection Regulation (GDPR) in the European Union. Typically, detection systems based on deep learning require annotated data for training. Collecting and annotating such data, however, is highly time-consuming and due to manual treatments not necessarily error free. Therefore, this paper presents a privacy-compliant approach based on Micro-Electro-Mechanical Systems LiDAR (MEMS-LiDAR), which exclusively captures anonymized 3D point clouds and avoids personal identification features. To compensate for the large amount of time required to record real LiDAR data and for post-processing and annotation, real recordings are augmented with synthetically generated scenes from the CARLA simulation framework. The results demonstrate that the hybrid data improves the average precision by 44 percentage points compared to a model trained exclusively with real data while reducing the manual annotation effort by 50 %. Thus, the proposed approach provides a scalable, cost-efficient alternative to purely real-data-based methods and systematically shows how synthetic LiDAR data can combine high performance in person detection with GDPR compliance in an industrial environment. --- ### A Provable Expressiveness Hierarchy in Hybrid Linear-Full Attention Authors: Xiaowei Ye, Xiaoyu He, Chao Liao, Chen Wu, Pinyan Lu Published: 2026-02-02 Categories: cs.LG, cs.AI, cs.CC arXiv: https://arxiv.org/abs/2602.01763v1 Transformers serve as the foundation of most modern large language models. To mitigate the quadratic complexity of standard full attention, various efficient attention mechanisms, such as linear and hybrid attention, have been developed. A fundamental gap remains: their expressive power relative to full attention lacks a rigorous theoretical characterization. In this work, we theoretically characterize the performance differences among these attention mechanisms. Our theory applies to all linear attention variants that can be formulated as a recurrence, including Mamba, DeltaNet, etc. Specifically, we establish an expressiveness hierarchy: for the sequential function composition-a multi-step reasoning task that must occur within a model's forward pass, an ($L+1$)-layer full attention network is sufficient, whereas any hybrid network interleaving $L-1$ layers of full attention with a substantially larger number ($2^{3L^2}$) of linear attention layers cannot solve it. This result demonstrates a clear separation in expressive power between the two types of attention. Our work provides the first provable separation between hybrid attention and standard full attention, offering a theoretical perspective for understanding the fundamental capabilities and limitations of different attention mechanisms. --- ### PRISM: Parametrically Refactoring Inference for Speculative Sampling Draft Models Authors: Xuliang Wang, Yuetao Chen, Maochan Zhen, Fang Liu, Xinzhou Zheng, Xingwu Liu, Hong Xu, Ming Li Published: 2026-02-02 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.01762v1 Large Language Models (LLMs), constrained by their auto-regressive nature, suffer from slow decoding. Speculative decoding methods have emerged as a promising solution to accelerate LLM decoding, attracting attention from both systems and AI research communities. Recently, the pursuit of better draft quality has driven a trend toward parametrically larger draft models, which inevitably introduces substantial computational overhead. While existing work attempts to balance the trade-off between prediction accuracy and compute latency, we address this fundamental dilemma through architectural innovation. We propose PRISM, which disaggregates the computation of each predictive step across different parameter sets, refactoring the computational pathways of draft models to successfully decouple model capacity from inference cost. Through extensive experiments, we demonstrate that PRISM outperforms all existing draft architectures, achieving exceptional acceptance lengths while maintaining minimal draft latency for superior end-to-end speedup. We also re-examine scaling laws with PRISM, revealing that PRISM scales more effectively with expanding data volumes than other draft architectures. Through rigorous and fair comparison, we show that PRISM boosts the decoding throughput of an already highly optimized inference engine by more than 2.6x. --- ### MagicFuse: Single Image Fusion for Visual and Semantic Reinforcement Authors: Hao Zhang, Yanping Zha, Zizhuo Li, Meiqi Gong, Jiayi Ma Published: 2026-02-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.01760v2 This paper focuses on a highly practical scenario: how to continue benefiting from the advantages of multi-modal image fusion under harsh conditions when only visible imaging sensors are available. To achieve this goal, we propose a novel concept of single-image fusion, which extends conventional data-level fusion to the knowledge level. Specifically, we develop MagicFuse, a novel single image fusion framework capable of deriving a comprehensive cross-spectral scene representation from a single low-quality visible image. MagicFuse first introduces an intra-spectral knowledge reinforcement branch and a cross-spectral knowledge generation branch based on the diffusion models. They mine scene information obscured in the visible spectrum and learn thermal radiation distribution patterns transferred to the infrared spectrum, respectively. Building on them, we design a multi-domain knowledge fusion branch that integrates the probabilistic noise from the diffusion streams of these two branches, from which a cross-spectral scene representation can be obtained through successive sampling. Then, we impose both visual and semantic constraints to ensure that this scene representation can satisfy human observation while supporting downstream semantic decision-making. Extensive experiments show that our MagicFuse achieves visual and semantic representation performance comparable to or even better than state-of-the-art fusion methods with multi-modal inputs, despite relying solely on a single degraded visible image. The code is publicly available at https://github.com/zhayanping/MagicFuse. --- ### Zero2Text: Zero-Training Cross-Domain Inversion Attacks on Textual Embeddings Authors: Doohyun Kim, Donghwa Kang, Kyungjae Lee, Hyeongboo Baek, Brent Byunghoon Kang Published: 2026-02-02 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.01757v2 The proliferation of retrieval-augmented generation (RAG) has established vector databases as critical infrastructure, yet they introduce severe privacy risks via embedding inversion attacks. Existing paradigms face a fundamental trade-off: optimization-based methods require computationally prohibitive queries, while alignment-based approaches hinge on the unrealistic assumption of accessible in-domain training data. These constraints render them ineffective in strict black-box and cross-domain settings. To dismantle these barriers, we introduce Zero2Text, a novel training-free framework based on recursive online alignment. Unlike methods relying on static datasets, Zero2Text synergizes LLM priors with a dynamic ridge regression mechanism to iteratively align generation to the target embedding on-the-fly. We further demonstrate that standard defenses, such as differential privacy, fail to effectively mitigate this adaptive threat. Extensive experiments across diverse benchmarks validate Zero2Text; notably, on MS MARCO against the OpenAI victim model, it achieves 1.8x higher ROUGE-L and 6.4x higher BLEU-2 scores compared to baselines, recovering sentences from unknown domains without a single leaked data pair. --- ### Mind-Brush: Integrating Agentic Cognitive Search and Reasoning into Image Generation Authors: Jun He, Junyan Ye, Zilong Huang, Dongzhi Jiang, Chenjue Zhang, Leqi Zhu, Renrui Zhang, Xiang Zhang, Weijia Li Published: 2026-02-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.01756v1 While text-to-image generation has achieved unprecedented fidelity, the vast majority of existing models function fundamentally as static text-to-pixel decoders. Consequently, they often fail to grasp implicit user intentions. Although emerging unified understanding-generation models have improved intent comprehension, they still struggle to accomplish tasks involving complex knowledge reasoning within a single model. Moreover, constrained by static internal priors, these models remain unable to adapt to the evolving dynamics of the real world. To bridge these gaps, we introduce Mind-Brush, a unified agentic framework that transforms generation into a dynamic, knowledge-driven workflow. Simulating a human-like 'think-research-create' paradigm, Mind-Brush actively retrieves multimodal evidence to ground out-of-distribution concepts and employs reasoning tools to resolve implicit visual constraints. To rigorously evaluate these capabilities, we propose Mind-Bench, a comprehensive benchmark comprising 500 distinct samples spanning real-time news, emerging concepts, and domains such as mathematical and Geo-Reasoning. Extensive experiments demonstrate that Mind-Brush significantly enhances the capabilities of unified models, realizing a zero-to-one capability leap for the Qwen-Image baseline on Mind-Bench, while achieving superior results on established benchmarks like WISE and RISE. --- ### Spot-Wise Smart Parking: An Edge-Enabled Architecture with YOLOv11 and Digital Twin Integration Authors: Gustavo P. C. P. da Luz, Alvaro M. Aspilcueta Narvaez, Tiago Godoi Bannwart, Gabriel Massuyoshi Sato, Luis Fernando Gomez Gonzalez, Juliana Freitag Borin Published: 2026-02-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.01754v1 Smart parking systems help reduce congestion and minimize users' search time, thereby contributing to smart city adoption and enhancing urban mobility. In previous works, we presented a system developed on a university campus to monitor parking availability by estimating the number of free spaces from vehicle counts within a region of interest. Although this approach achieved good accuracy, it restricted the system's ability to provide spot-level insights and support more advanced applications. To overcome this limitation, we extend the system with a spot-wise monitoring strategy based on a distance-aware matching method with spatial tolerance, enhanced through an Adaptive Bounding Box Partitioning method for challenging spaces. The proposed approach achieves a balanced accuracy of 98.80% while maintaining an inference time of 8 seconds on a resource-constrained edge device, enhancing the capabilities of YOLOv11m, a model that has a size of 40.5 MB. In addition, two new components were introduced: (i) a Digital Shadow that visually represents parking lot entities as a base to evolve to a full Digital Twin, and (ii) an application support server based on a repurposed TV box. The latter not only enables scalable communication among cloud services, the parking totem, and a bot that provides detailed spot occupancy statistics, but also promotes hardware reuse as a step towards greater sustainability. --- ### ObjEmbed: Towards Universal Multimodal Object Embeddings Authors: Shenghao Fu, Yukun Su, Fengyun Rao, Jing Lyu, Xiaohua Xie, Wei-Shi Zheng Published: 2026-02-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.01753v3 Aligning objects with corresponding textual descriptions is a fundamental challenge and a realistic requirement in vision-language understanding. While recent multimodal embedding models excel at global image-text alignment, they often struggle with fine-grained alignment between image regions and specific phrases. In this work, we present ObjEmbed, a novel MLLM embedding model that decomposes the input image into multiple regional embeddings, each corresponding to an individual object, along with global embeddings. It supports a wide range of visual understanding tasks like visual grounding, local image retrieval, and global image retrieval. ObjEmbed enjoys three key properties: (1) Object-Oriented Representation: It captures both semantic and spatial aspects of objects by generating two complementary embeddings for each region: an object embedding for semantic matching and an IoU embedding that predicts localization quality. The final object matching score combines semantic similarity with the predicted IoU, enabling more accurate retrieval. (2) Versatility: It seamlessly handles both region-level and image-level tasks. (3) Efficient Encoding: All objects in an image, along with the full image, are encoded in a single forward pass for high efficiency. Superior performance on 18 diverse benchmarks demonstrates its strong semantic discrimination. --- ### WorldCup Sampling for Multi-bit LLM Watermarking Authors: Yidan Wang, Yubing Ren, Yanan Cao, Li Guo Published: 2026-02-02 Categories: cs.CL, cs.CR arXiv: https://arxiv.org/abs/2602.01752v2 As large language models (LLMs) generate increasingly human-like text, watermarking has emerged as a promising solution for reliable attribution beyond mere detection. While multi-bit watermarking enables richer provenance encoding, existing approaches typically extend zero-bit watermarking schemes by introducing static logit perturbations and counting-based decoding strategies, which can degrade text quality and compromise decoding robustness as the payload increases. In this paper, we propose WorldCup, a multi-bit watermarking framework for LLMs that models the sampling process as a structured communication channel and embeds message bits through a hierarchical competition mechanism guided by complementary signals. Moreover, WorldCup incorporates entropy-aware modulation to preserve generation quality and enables robust message recovery via confidence-aware decoding that accounts for token-level reliability. Comprehensive experiments demonstrate that WorldCup achieves a strong balance across message capacity, detectability, robustness, text quality, and decoding efficiency, consistently outperforming prior baselines. We believe that this work establishes a scalable and principled foundation for future research on multi-bit watermarking in LLMs. --- ### MGKAN: Predicting Asymmetric Drug-Drug Interactions via a Multimodal Graph Kolmogorov-Arnold Network Authors: Kunyi Fan, Mengjie Chen, Longlong Li, Cunquan Qu Published: 2026-02-02 Categories: cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2602.01751v2 Predicting drug-drug interactions (DDIs) is essential for safe pharmacological treatments. Previous graph neural network (GNN) models leverage molecular structures and interaction networks but mostly rely on linear aggregation and symmetric assumptions, limiting their ability to capture nonlinear and heterogeneous patterns. We propose MGKAN, a Graph Kolmogorov-Arnold Network that introduces learnable basis functions into asymmetric DDI prediction. MGKAN replaces conventional MLP transformations with KAN-driven basis functions, enabling more expressive and nonlinear modeling of drug relationships. To capture pharmacological dependencies, MGKAN integrates three network views-an asymmetric DDI network, a co-interaction network, and a biochemical similarity network-with role-specific embeddings to preserve directional semantics. A fusion module combines linear attention and nonlinear transformation to enhance representational capacity. On two benchmark datasets, MGKAN outperforms seven state-of-the-art baselines. Ablation studies and case studies confirm its predictive accuracy and effectiveness in modeling directional drug effects. --- ### Adversarial Reward Auditing for Active Detection and Mitigation of Reward Hacking Authors: Mohammad Beigi, Ming Jin, Junshan Zhang, Qifan Wang, Lifu Huang Published: 2026-02-02 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.01750v2 Reinforcement Learning from Human Feedback (RLHF) remains vulnerable to reward hacking, where models exploit spurious correlations in learned reward models to achieve high scores while violating human intent. Existing mitigations rely on static defenses that cannot adapt to novel exploitation strategies. We propose Adversarial Reward Auditing (ARA), a framework that reconceptualizes reward hacking as a dynamic, competitive game. ARA operates in two stages: first, a Hacker policy discovers reward model vulnerabilities while an Auditor learns to detect exploitation from latent representations; second, Auditor-Guided RLHF (AG-RLHF) gates reward signals to penalize detected hacking, transforming reward hacking from an unobservable failure into a measurable, controllable signal. Experiments across three hacking scenarios demonstrate that ARA achieves the best alignment-utility tradeoff among all baselines: reducing sycophancy to near-SFT levels while improving helpfulness, decreasing verbosity while achieving the highest ROUGE-L, and suppressing code gaming while improving Pass@1. Beyond single-domain evaluation, we show that reward hacking, detection, and mitigation all generalize across domains -- a Hacker trained on code gaming exhibits increased sycophancy despite no reward for this behavior, and an Auditor trained on one domain effectively suppresses exploitation in others, enabling efficient multi-domain defense with a single model. --- ### Adversarial Reward Auditing for Active Detection and Mitigation of Reward Hacking Authors: Mohammad Beigi, Ming Jin, Junshan Zhang, Qifan Wang, Lifu Huang Published: 2026-02-02 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.01750v1 Reinforcement Learning from Human Feedback (RLHF) remains vulnerable to reward hacking, where models exploit spurious correlations in learned reward models to achieve high scores while violating human intent. Existing mitigations rely on static defenses that cannot adapt to novel exploitation strategies. We propose Adversarial Reward Auditing (ARA), a framework that reconceptualizes reward hacking as a dynamic, competitive game. ARA operates in two stages: first, a Hacker policy discovers reward model vulnerabilities while an Auditor learns to detect exploitation from latent representations; second, Auditor-Guided RLHF (AG-RLHF) gates reward signals to penalize detected hacking, transforming reward hacking from an unobservable failure into a measurable, controllable signal. Experiments across three hacking scenarios demonstrate that ARA achieves the best alignment-utility tradeoff among all baselines: reducing sycophancy to near-SFT levels while improving helpfulness, decreasing verbosity while achieving the highest ROUGE-L, and suppressing code gaming while improving Pass@1. Beyond single-domain evaluation, we show that reward hacking, detection, and mitigation all generalize across domains -- a Hacker trained on code gaming exhibits increased sycophancy despite no reward for this behavior, and an Auditor trained on one domain effectively suppresses exploitation in others, enabling efficient multi-domain defense with a single model. --- ### Controlling Exploration-Exploitation in GFlowNets via Markov Chain Perspectives Authors: Lin Chen, Samuel Drapeau, Fanghao Shao, Xuekai Zhu, Bo Xue, Yunchong Song, Mathieu Laurière, Zhouhan Lin Published: 2026-02-02 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.01749v3 Generative Flow Network (GFlowNet) objectives implicitly fix an equal mixing of forward and backward policies, potentially constraining the exploration-exploitation trade-off during training. By further exploring the link between GFlowNets and Markov chains, we establish an equivalence between GFlowNet objectives and Markov chain reversibility, thereby revealing the origin of such constraints, and provide a framework for adapting Markov chain properties to GFlowNets. Building on these theoretical findings, we propose $α$-GFNs, which generalize the mixing via a tunable parameter $α$. This generalization enables direct control over exploration-exploitation dynamics to enhance mode discovery capabilities, while ensuring convergence to unique flows. Across various benchmarks, including Set, Bit Sequence, and Molecule Generation, $α$-GFN objectives consistently outperform previous GFlowNet objectives, achieving up to a $10 \times$ increase in the number of discovered modes. --- ### Enhancing Automated Essay Scoring With Three Techniques: Two-Stage Fine-Tuning, Score Alignment, and Self-Training Authors: Hongseok Choi, Serynn Kim, Wencke Liermann, Jin Seong, Jin-Xia Huang Published: 2026-02-02 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.01747v2 Automated Essay Scoring (AES) plays a crucial role in education by providing scalable and efficient assessment tools. However, in real-world settings, the extreme scarcity of labeled data severely limits the development and practical adoption of robust AES systems. This study proposes a novel approach to enhance AES performance in both limited-data and full-data settings by introducing three key techniques. First, we introduce a Two-Stage fine-tuning strategy that leverages low-rank adaptations to better adapt an AES model to target prompt essays. Second, we introduce a Score Alignment technique to improve consistency between predicted and true score distributions. Third, we employ uncertainty-aware self-training using unlabeled data, effectively expanding the training set with pseudo-labeled samples while mitigating label noise propagation. We implement the above three key techniques on DualBERT. We conduct extensive experiments on the ASAP++ dataset, and additionally evaluate the proposed techniques on two other datasets, TOEFL11 and ELLIPSE, to examine their generalizability. In the 32-data setting on ASAP++, all three key techniques improve performance, and their integration achieves 91.2% of the full-data performance trained on approximately 1,000 labeled samples. In addition, the proposed Score Alignment technique consistently improves performance in both limited-data and full-data settings: e.g., it achieves state-of-the-art results in the full-data setting on ASAP++ when integrated into DualBERT. --- ### Enhancing Automated Essay Scoring with Three Techniques: Two-Stage Fine-Tuning, Score Alignment, and Self-Training Authors: Hongseok Choi, Serynn Kim, Wencke Liermann, Jin Seong, Jin-Xia Huang Published: 2026-02-02 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.01747v1 Automated Essay Scoring (AES) plays a crucial role in education by providing scalable and efficient assessment tools. However, in real-world settings, the extreme scarcity of labeled data severely limits the development and practical adoption of robust AES systems. This study proposes a novel approach to enhance AES performance in both limited-data and full-data settings by introducing three key techniques. First, we introduce a Two-Stage fine-tuning strategy that leverages low-rank adaptations to better adapt an AES model to target prompt essays. Second, we introduce a Score Alignment technique to improve consistency between predicted and true score distributions. Third, we employ uncertainty-aware self-training using unlabeled data, effectively expanding the training set with pseudo-labeled samples while mitigating label noise propagation. We implement above three key techniques on DualBERT. We conduct extensive experiments on the ASAP++ dataset. As a result, in the 32-data setting, all three key techniques improve performance, and their integration achieves 91.2% of the full-data performance trained on approximately 1,000 labeled samples. In addition, the proposed Score Alignment technique consistently improves performance in both limited-data and full-data settings: e.g., it achieves state-of-the-art results in the full-data setting when integrated into DualBERT. --- ### Rethinking LoRA for Data Heterogeneous Federated Learning: Subspace and State Alignment Authors: Hongyi Peng, Han Yu, Xiaoxiao Li, Qiang Yang Published: 2026-02-02 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.01746v1 Low-Rank Adaptation (LoRA) is widely used for federated fine-tuning. Yet under non-IID settings, it can substantially underperform full-parameter fine-tuning. Through with-high-probability robustness analysis, we uncover that this gap can be attributed to two coupled mismatches: (i) update-space mismatch, where clients optimize in a low-rank subspace but aggregation occurs in the full space; and (ii) optimizer-state mismatch, where unsynchronized adaptive states amplify drift across rounds. We propose FedGaLore, which combines client-side GaLore-style gradient-subspace optimization with server-side drift-robust synchronization of projected second-moment states via spectral shared-signal extraction, to address this challenge. Across NLU, vision, and NLG benchmarks, FedGaLore improves robustness and accuracy over state-of-the-art federated LoRA baselines in non-IID settings. --- ### Probability-Entropy Calibration: An Elastic Indicator for Adaptive Fine-tuning Authors: Wenhao Yu, Shaohang Wei, Jiahong Liu, Yifan Li, Minda Hu, Aiwei Liu, Hao Zhang, Irwin King Published: 2026-02-02 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.01745v2 Token-level reweighting is a simple yet effective mechanism for controlling supervised fine-tuning, but common indicators are largely one-dimensional: the ground-truth probability reflects downstream alignment, while token entropy reflects intrinsic uncertainty induced by the pre-training prior. Ignoring entropy can misidentify noisy or easily replaceable tokens as learning-critical, while ignoring probability fails to reflect target-specific alignment. RankTuner introduces a probability--entropy calibration signal, the Relative Rank Indicator, which compares the rank of the ground-truth token with its expected rank under the prediction distribution. The inverse indicator is used as a token-wise Relative Scale to reweight the fine-tuning objective, focusing updates on truly under-learned tokens without over-penalizing intrinsically uncertain positions. Experiments on multiple backbones show consistent improvements on mathematical reasoning benchmarks, transfer gains on out-of-distribution reasoning, and pre code generation performance over probability-only or entropy-only reweighting baselines. --- ### Softmax Linear Attention: Reclaiming Global Competition Authors: Mingwei Xu, Xuan Lin, Xinnan Guo, Wanqing Xu, Wanyun Cui Published: 2026-02-02 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.01744v1 While linear attention reduces the quadratic complexity of standard Transformers to linear time, it often lags behind in expressivity due to the removal of softmax normalization. This omission eliminates \emph{global competition}, a critical mechanism that enables models to sharply focus on relevant information amidst long-context noise. In this work, we propose \textbf{Softmax Linear Attention (SLA)}, a framework designed to restore this competitive selection without sacrificing efficiency. By lifting the softmax operation from the token level to the head level, SLA leverages attention heads as coarse semantic slots, applying a competitive gating mechanism to dynamically select the most relevant subspaces. This reintroduces the ``winner-take-all'' dynamics essential for precise retrieval and robust long-context understanding. Distinct from prior methods that focus on refining local kernel functions, SLA adopts a broader perspective by exploiting the higher-level multi-head aggregation structure. Extensive experiments demonstrate that SLA consistently enhances state-of-the-art linear baselines (RetNet, GLA, GDN) across language modeling and long-context benchmarks, particularly in challenging retrieval scenarios where it significantly boosts robustness against noise, validating its capability to restore precise focus while maintaining linear complexity. --- ### Tail-Aware Post-Training Quantization for 3D Geometry Models Authors: Sicheng Pan, Chen Tang, Shuzhao Xie, Ke Yang, Weixiang Zhang, Jiawei Li, Bin Chen, Shu-Tao Xia, Zhi Wang Published: 2026-02-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.01741v1 The burgeoning complexity and scale of 3D geometry models pose significant challenges for deployment on resource-constrained platforms. While Post-Training Quantization (PTQ) enables efficient inference without retraining, conventional methods, primarily optimized for 2D Vision Transformers, fail to transfer effectively to 3D models due to intricate feature distributions and prohibitive calibration overhead. To address these challenges, we propose TAPTQ, a Tail-Aware Post-Training Quantization pipeline specifically engineered for 3D geometric learning. Our contribution is threefold: (1) To overcome the data-scale bottleneck in 3D datasets, we develop a progressive coarse-to-fine calibration construction strategy that constructs a highly compact subset to achieve both statistical purity and geometric representativeness. (2) We reformulate the quantization interval search as an optimization problem and introduce a ternary-search-based solver, reducing the computational complexity from $\mathcal{O}(N)$ to $\mathcal{O}(\log N)$ for accelerated deployment. (3) To mitigate quantization error accumulation, we propose TRE-Guided Module-wise Compensation, which utilizes a Tail Relative Error (TRE) metric to adaptively identify and rectify distortions in modules sensitive to long-tailed activation outliers. Extensive experiments on the VGGT and Pi3 benchmarks demonstrate that TAPTQ consistently outperforms state-of-the-art PTQ methods in accuracy while significantly reducing calibration time. The code will be released soon. --- ### MACD: Model-Aware Contrastive Decoding via Counterfactual Data Authors: Qixin Xiao, Kun Zhou Published: 2026-02-02 Categories: cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.01740v3 Video language models (Video-LLMs) are prone to hallucinations, generating plausible but ungrounded content when visual evidence is weak, ambiguous, or biased. Existing methods, such as contrastive decoding (CD), rely on random perturbations to construct contrastive data for hallucination mitigation, but often fail to target the visual cues that drive hallucination or align with model weaknesses. We propose Model-Aware Counterfactual Data based Contrastive Decoding (MACD), an inference strategy that combines model-guided counterfactual construction with contrastive decoding. MACD uses the Video-LLM's own feedback to identify object regions most responsible for hallucination, generating targeted object-level counterfactual inputs rather than arbitrary frame or temporal modifications. These counterfactual inputs are integrated into CD to enforce evidence-grounded token selection during decoding. Experiments on EventHallusion, MVBench, Perception-test, and Video-MME show that MACD consistently reduces hallucination while maintaining or improving task accuracy across diverse Video-LLMs, including Qwen and InternVL, with especially strong gains in scenarios involving small, occluded, or co-occurring objects. --- ### Simplicity Prevails: The Emergence of Generalizable AIGI Detection in Visual Foundation Models Authors: Yue Zhou, Xinan He, Kaiqing Lin, Bing Fan, Feng Ding, Bin Li Published: 2026-02-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.01738v2 While specialized detectors for AI-Generated Images (AIGI) achieve near-perfect accuracy on curated benchmarks, they suffer from a dramatic performance collapse in realistic, in-the-wild scenarios. In this work, we demonstrate that simplicity prevails over complex architectural designs. A simple linear classifier trained on the frozen features of modern Vision Foundation Models , including Perception Encoder, MetaCLIP 2, and DINOv3, establishes a new state-of-the-art. Through a comprehensive evaluation spanning traditional benchmarks, unseen generators, and challenging in-the-wild distributions, we show that this baseline not only matches specialized detectors on standard benchmarks but also decisively outperforms them on in-the-wild datasets, boosting accuracy by striking margins of over 30\%. We posit that this superior capability is an emergent property driven by the massive scale of pre-training data containing synthetic content. We trace the source of this capability to two distinct manifestations of data exposure: Vision-Language Models internalize an explicit semantic concept of forgery, while Self-Supervised Learning models implicitly acquire discriminative forensic features from the pretraining data. However, we also reveal persistent limitations: these models suffer from performance degradation under recapture and transmission, remain blind to VAE reconstruction and localized editing. We conclude by advocating for a paradigm shift in AI forensics, moving from overfitting on static benchmarks to harnessing the evolving world knowledge of foundation models for real-world reliability. --- ### Physics-Informed Chebyshev Polynomial Neural Operator for Parametric Partial Differential Equations Authors: Biao Chen, Jing Wang, Hairun Xie, Qineng Wang, Shuai Zhang, Yifan Xia, Jifa Zhang Published: 2026-02-02 Categories: physics.flu-dyn, cs.LG arXiv: https://arxiv.org/abs/2602.01737v1 Neural operators have emerged as powerful deep learning frameworks for approximating solution operators of parameterized partial differential equations (PDE). However, current methods predominantly rely on multilayer perceptrons (MLPs) for mapping inputs to solutions, which impairs training robustness in physics-informed settings due to inherent spectral biases and fixed activation functions. To overcome the architectural limitations, we introduce the Physics-Informed Chebyshev Polynomial Neural Operator (CPNO), a novel mesh-free framework that leverages a basis transformation to replace unstable monomial expansions with the numerically stable Chebyshev spectral basis. By integrating parameter dependent modulation mechanism to main net, CPNO constructs PDE solutions in a near-optimal functional space, decoupling the model from MLP-specific constraints and enhancing multi-scale representation. Theoretical analysis demonstrates the Chebyshev basis's near-minimax uniform approximation properties and superior conditioning, with Lebesgue constants growing logarithmically with degree, thereby mitigating spectral bias and ensuring stable gradient flow during optimization. Numerical experiments on benchmark parameterized PDEs show that CPNO achieves superior accuracy, faster convergence, and enhanced robustness to hyperparameters. The experiment of transonic airfoil flow has demonstrated the capability of CPNO in characterizing complex geometric problems. --- ### Position: The Inevitable End of One-Architecture-Fits-All-Domains in Time Series Forecasting Authors: Qinwei Ma, Jingzhe Shi, Jiahao Qiu, Zaiwen Yang Published: 2026-02-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.01736v1 Recent work has questioned the effectiveness and robustness of neural network architectures for time series forecasting tasks. We summarize these concerns and analyze groundly their inherent limitations: i.e. the irreconcilable conflict between single (or few similar) domains SOTA and generalizability over general domains for time series forecasting neural network architecture designs. Moreover, neural networks architectures for general domain time series forecasting are becoming more and more complicated and their performance has almost saturated in recent years. As a result, network architectures developed aiming at fitting general time series domains are almost not inspiring for real world practices for certain single (or few similar) domains such as Finance, Weather, Traffic, etc: each specific domain develops their own methods that rarely utilize advances in neural network architectures of time series community in recent 2-3 years. As a result, we call for the time series community to shift focus away from research on time series neural network architectures for general domains: these researches have become saturated and away from domain-specific SOTAs over time. We should either (1) focus on deep learning methods for certain specific domain(s), or (2) turn to the development of meta-learning methods for general domains. --- ### MSign: An Optimizer Preventing Training Instability in Large Language Models via Stable Rank Restoration Authors: Lianhai Ren, Yucheng Ding, Xiao Liu, Peng Cheng, Yeyun Gong Published: 2026-02-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.01734v2 Training instability remains a critical challenge in large language model (LLM) pretraining, often manifesting as sudden gradient explosions that waste significant computational resources. We study training failures in a 5M-parameter NanoGPT model scaled via $μ$P, identifying two key phenomena preceding collapse: (1) rapid decline in weight matrix stable rank (ratio of squared Frobenius norm to squared spectral norm), and (2) increasing alignment between adjacent layer Jacobians. We prove theoretically that these two conditions jointly cause exponential gradient norm growth with network depth. To break this instability mechanism, we propose MSign, a new optimizer that periodically applies matrix sign operations to restore stable rank. Experiments on models from 5M to 3B parameters demonstrate that MSign effectively prevents training failures with a computational overhead of less than 7.0%. --- ### MSign: An Optimizer Preventing Training Instability in Large Language Models via Stable Rank Restoration Authors: Lianhai Ren, Yucheng Ding, Xiao Liu, Qianxiao Li, Peng Cheng, Yeyun Gong Published: 2026-02-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.01734v1 Training instability remains a critical challenge in large language model (LLM) pretraining, often manifesting as sudden gradient explosions that waste significant computational resources. We study training failures in a 5M-parameter NanoGPT model scaled via $μ$P, identifying two key phenomena preceding collapse: (1) rapid decline in weight matrix stable rank (ratio of squared Frobenius norm to squared spectral norm), and (2) increasing alignment between adjacent layer Jacobians. We prove theoretically that these two conditions jointly cause exponential gradient norm growth with network depth. To break this instability mechanism, we propose MSign, a new optimizer that periodically applies matrix sign operations to restore stable rank. Experiments on models from 5M to 3B parameters demonstrate that MSign effectively prevents training failures with a computational overhead of less than 7.0%. --- ### Improving Backward Conformal Prediction via Non-Conformity Score Transformation Authors: Junxian Liu, Hao Zeng, Hongxin Wei Published: 2026-02-02 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2602.01733v3 Conformal Prediction (CP) provides a statistical framework for uncertainty quantification that constructs prediction sets with coverage guarantees. While CP yields uncontrolled prediction set sizes, Backward Conformal Prediction (BCP) inverts this paradigm by enforcing a predefined upper bound on set size and estimating the resulting coverage guarantee. However, the looseness induced by Markov's inequality within the BCP framework causes a significant gap between the estimated coverage bound and the empirical coverage. In this work, we introduce ST-BCP, a novel method that introduces a data-dependent transformation of nonconformity scores to narrow the coverage gap. In particular, we develop a computable transformation and prove that it outperforms the baseline identity transformation. Extensive experiments demonstrate the effectiveness of our method, reducing the average coverage gap from 4.20\% to 1.12\% on common benchmarks. --- ### Cross-Domain Fake News Detection on Unseen Domains via LLM-Based Domain-Aware User Modeling Authors: Xuankai Yang, Yan Wang, Jiajie Zhu, Pengfei Ding, Hongyang Liu, Xiuzhen Zhang, Huan Liu Published: 2026-02-02 Categories: cs.SI, cs.LG arXiv: https://arxiv.org/abs/2602.01726v1 Cross-domain fake news detection (CD-FND) transfers knowledge from a source domain to a target domain and is crucial for real-world fake news mitigation. This task becomes particularly important yet more challenging when the target domain is previously unseen (e.g., the COVID-19 outbreak or the Russia-Ukraine war). However, existing CD-FND methods overlook such scenarios and consequently suffer from the following two key limitations: (1) insufficient modeling of high-level semantics in news and user engagements; and (2) scarcity of labeled data in unseen domains. Targeting these limitations, we find that large language models (LLMs) offer strong potential for CD-FND on unseen domains, yet their effective use remains non-trivial. Nevertheless, two key challenges arise: (1) how to capture high-level semantics from both news content and user engagements using LLMs; and (2) how to make LLM-generated features more reliable and transferable for CD-FND on unseen domains. To tackle these challenges, we propose DAUD, a novel LLM-Based Domain-Aware framework for fake news detection on Unseen Domains. DAUD employs LLMs to extract high-level semantics from news content. It models users' single- and cross-domain engagements to generate domain-aware behavioral representations. In addition, DAUD captures the relations between original data-driven features and LLM-derived features of news, users, and user engagements. This allows it to extract more reliable domain-shared representations that improve knowledge transfer to unseen domains. Extensive experiments on real-world datasets demonstrate that DAUD outperforms state-of-the-art baselines in both general and unseen-domain CD-FND settings. --- ### SafePred: A Predictive Guardrail for Computer-Using Agents via World Models Authors: Yurun Chen, Zeyi Liao, Ping Yin, Taotao Xie, Keting Yin, Shengyu Zhang Published: 2026-02-02 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.01725v1 With the widespread deployment of Computer-using Agents (CUAs) in complex real-world environments, prevalent long-term risks often lead to severe and irreversible consequences. Most existing guardrails for CUAs adopt a reactive approach, constraining agent behavior only within the current observation space. While these guardrails can prevent immediate short-term risks (e.g., clicking on a phishing link), they cannot proactively avoid long-term risks: seemingly reasonable actions can lead to high-risk consequences that emerge with a delay (e.g., cleaning logs leads to future audits being untraceable), which reactive guardrails cannot identify within the current observation space. To address these limitations, we propose a predictive guardrail approach, with the core idea of aligning predicted future risks with current decisions. Based on this approach, we present SafePred, a predictive guardrail framework for CUAs that establishes a risk-to-decision loop to ensure safe agent behavior. SafePred supports two key abilities: (1) Short- and long-term risk prediction: by using safety policies as the basis for risk prediction, SafePred leverages the prediction capability of the world model to generate semantic representations of both short-term and long-term risks, thereby identifying and pruning actions that lead to high-risk states; (2) Decision optimization: translating predicted risks into actionable safe decision guidances through step-level interventions and task-level re-planning. Extensive experiments show that SafePred significantly reduces high-risk behaviors, achieving over 97.6% safety performance and improving task utility by up to 21.4% compared with reactive baselines. --- ### DenVisCoM: Dense Vision Correspondence Mamba for Efficient and Real-time Optical Flow and Stereo Estimation Authors: Tushar Anand, Maheswar Bora, Antitza Dantcheva, Abhijit Das Published: 2026-02-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.01724v1 In this work, we propose a novel Mamba block DenVisCoM, as well as a novel hybrid architecture specifically tailored for accurate and real-time estimation of optical flow and disparity estimation. Given that such multi-view geometry and motion tasks are fundamentally related, we propose a unified architecture to tackle them jointly. Specifically, the proposed hybrid architecture is based on DenVisCoM and a Transformer-based attention block that efficiently addresses real-time inference, memory footprint, and accuracy at the same time for joint estimation of motion and 3D dense perception tasks. We extensively analyze the benchmark trade-off of accuracy and real-time processing on a large number of datasets. Our experimental results and related analysis suggest that our proposed model can accurately estimate optical flow and disparity estimation in real time. All models and associated code are available at https://github.com/vimstereo/DenVisCoM. --- ### FastPhysGS: Accelerating Physics-based Dynamic 3DGS Simulation via Interior Completion and Adaptive Optimization Authors: Yikun Ma, Yiqing Li, Jingwen Ye, Zhongkai Wu, Weidong Zhang, Lin Gao, Zhi Jin Published: 2026-02-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.01723v1 Extending 3D Gaussian Splatting (3DGS) to 4D physical simulation remains challenging. Based on the Material Point Method (MPM), existing methods either rely on manual parameter tuning or distill dynamics from video diffusion models, limiting the generalization and optimization efficiency. Recent attempts using LLMs/VLMs suffer from a text/image-to-3D perceptual gap, yielding unstable physics behavior. In addition, they often ignore the surface structure of 3DGS, leading to implausible motion. We propose FastPhysGS, a fast and robust framework for physics-based dynamic 3DGS simulation:(1) Instance-aware Particle Filling (IPF) with Monte Carlo Importance Sampling (MCIS) to efficiently populate interior particles while preserving geometric fidelity; (2) Bidirectional Graph Decoupling Optimization (BGDO), an adaptive strategy that rapidly optimizes material parameters predicted from a VLM. Experiments show FastPhysGS achieves high-fidelity physical simulation in 1 minute using only 7 GB runtime memory, outperforming prior works with broad potential applications. --- ### COMI: Coarse-to-fine Context Compression via Marginal Information Gain Authors: Jiwei Tang, Shilei Liu, Zhicheng Zhang, Yujin Yuan, Libin Zheng, Wenbo Su, Bo Zheng Published: 2026-02-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.01719v3 Large Language Models (LLMs) have demonstrated exceptional capabilities across diverse tasks. However, their deployment in long context scenarios remains hindered by computational inefficiency and information redundancy. Context compression methods address these challenges by significantly reducing input length and eliminating redundancy. We propose COMI, a coarse-to-fine adaptive context compression framework that jointly optimizes for semantic relevance and diversity under high compression rates. We introduce Marginal Information Gain (MIG), a metric defined as the relevance of a unit to the input query minus its semantic redundancy with other units, guiding the compression process to prioritize information that is both relevant and low redundant. The framework operates in two stages: (1) Coarse-Grained Group Reallocation, where the context is partitioned into groups and dynamically assigned compression rates based on inter-group MIG, ensuring compression budgets align with information value distribution; and (2) Fine-Grained Token Merging, where tokens within each group are fused via an intra-group MIG-based weighting mechanism, thereby preserving key semantics while avoiding the accumulation of redundancy. Extensive experiments across question-answering (e.g., NaturalQuestions, 2WikiMQA, HotpotQA and NarrativeQA), summarization (e.g., MultiNews) with various backbones (e.g., LLaMA-2-7B, Qwen2-7B) show that COMI outperforms existing baselines by a large margin, e.g., approximately 25-point Exact Match (EM) improvement under 32x compression constraint with Qwen2-7B on NaturalQuestions. --- ### Generalization Measures under Controlled Covariate Shift: A Regime-Aware Benchmark Authors: Sora Nakai, Youssef Fadhloun, Kacem Mathlouthi, Kotaro Yoshida, Ganesh Talluri, Ioannis Mitliagkas, Hiroki Naganuma Published: 2026-02-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.01718v2 Predicting generalization from quantities available before target-test evaluation remains a central challenge in deep learning. The systematic benchmark of Jiang et al. (2020) evaluated many generalization measures, but it focused on independent and identically distributed (IID) settings. We revisit this problem for image classifiers evaluated under controlled corruptions and perturbations. Our study uses CIFAR-10-C/P, where the label space and task remain fixed while the input images are degraded or perturbed. This setting also allows us to revisit the robustness concerns raised by Dziugaite et al. (2020), who showed that the apparent reliability of generalization measures can depend strongly on experimental conditions. Our experiments show that the usefulness of generalization measures is strongly regime-dependent. In our exploratory decision analysis across three CNN-style architectures, sharpness- and input-gradient-based measures are among the leading individual signals, whereas family results are close and architecture dependent. Optimization-based measures, Information Criteria, and Sharpness-based measures provide additional regime-dependent signals in correlation or local-reliability analyses. Together, these findings suggest that model selection should not rely only on measures favored by IID evaluation. Instead, within the evaluated CIFAR-10-C/P setting and architectures, generalization measures should be treated as regime-dependent ranking signals whose utility must be evaluated for the intended corruption or perturbation setting. --- ### Revisiting Generalization Measures Beyond IID: An Empirical Study under Distributional Shift Authors: Sora Nakai, Youssef Fadhloun, Kacem Mathlouthi, Kotaro Yoshida, Ganesh Talluri, Ioannis Mitliagkas, Hiroki Naganuma Published: 2026-02-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.01718v1 Generalization remains a central yet unresolved challenge in deep learning, particularly the ability to predict a model's performance beyond its training distribution using quantities available prior to test-time evaluation. Building on the large-scale study of Jiang et al. (2020). and concerns by Dziugaite et al. (2020). about instability across training configurations, we benchmark the robustness of generalization measures beyond IID regime. We train small-to-medium models over 10,000 hyperparameter configurations and evaluate more than 40 measures computable from the trained model and the available training data alone. We significantly broaden the experimental scope along multiple axes: (i) extending the evaluation beyond the standard IID setting to include benchmarking for robustness across diverse distribution shifts, (ii) evaluating multiple architectures and training recipes, and (iii) newly incorporating calibration- and information-criteria-based measures to assess their alignment with both IID and OOD generalization. We find that distribution shifts can substantially alter the predictive performance of many generalization measures, while a smaller subset remains comparatively stable across settings. --- ### BBPE16: UTF-16-based byte-level byte-pair encoding for improved multilingual speech recognition Authors: Hyunsik Kim, Haeri Kim, Munhak Lee, Kyungmin Lee Published: 2026-02-02 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.01717v1 Multilingual automatic speech recognition (ASR) requires tokenization that efficiently covers many writing systems. Byte-level BPE (BBPE) using UTF-8 is widely adopted for its language-agnostic design and full Unicode coverage, but its variable-length encoding inflates token sequences for non-Latin scripts, such as Chinese, Japanese, and Korean (CJK). Longer sequences increase computational load and memory use. We propose BBPE16, a UTF-16-based BBPE tokenizer that represents most modern scripts with a uniform 2-byte code unit. BBPE16 preserves BBPE's language-agnostic properties while substantially improving cross-lingual token sharing. Across monolingual, bilingual, and trilingual ASR, and in a multilingual continual-learning setup, BBPE16 attains comparable or better accuracy; for Chinese, it reduces token counts by up to 10.4% and lowers decoding iterations by up to 10.3%. These reductions speed up fine-tuning and inference and decrease memory usage, making BBPE16 a practical tokenization choice for multilingual ASR. --- ### Mechanistic Indicators of Steering Effectiveness in Large Language Models Authors: Mehdi Jafari, Hao Xue, Flora Salim Published: 2026-02-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.01716v3 Activation-based steering enables Large Language Models (LLMs) to exhibit targeted behaviors by intervening on intermediate activations without retraining. Despite its widespread use, the mechanistic factors that govern when steering succeeds or fails remain poorly understood, as prior work has relied primarily on black-box outputs or LLM-based judges. In this study, we investigate whether the reliability of steering can be diagnosed using internal model signals. We focus on two information-theoretic measures: the entropy-derived Normalized Branching Factor (NBF), and the Kullback-Leibler (KL) divergence between steered activations and targeted concepts in the vocabulary space. We hypothesize that effective steering corresponds to structured entropy preservation and coherent KL alignment across decoding steps. Building on a reliability study demonstrating high inter-judge agreement between two architecturally distinct LLMs, we use LLM-generated annotations as ground truth and show that these mechanistic signals provide meaningful predictive power for identifying successful steering and estimating failure probability. We further introduce a stronger evaluation baseline for Contrastive Activation Addition (CAA) and Sparse Autoencoder-based steering, the two most widely adopted activation-steering methods. --- ### MedAraBench: Large-Scale Arabic Medical Question Answering Dataset and Benchmark Authors: Mouath Abu-Daoud, Leen Kharouf, Omar El Hajj, Dana El Samad, Mariam Al-Omari, Jihad Mallat, Khaled Saleh, Nizar Habash, Farah E. Shamout Published: 2026-02-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.01714v1 Arabic remains one of the most underrepresented languages in natural language processing research, particularly in medical applications, due to the limited availability of open-source data and benchmarks. The lack of resources hinders efforts to evaluate and advance the multilingual capabilities of Large Language Models (LLMs). In this paper, we introduce MedAraBench, a large-scale dataset consisting of Arabic multiple-choice question-answer pairs across various medical specialties. We constructed the dataset by manually digitizing a large repository of academic materials created by medical professionals in the Arabic-speaking region. We then conducted extensive preprocessing and split the dataset into training and test sets to support future research efforts in the area. To assess the quality of the data, we adopted two frameworks, namely expert human evaluation and LLM-as-a-judge. Our dataset is diverse and of high quality, spanning 19 specialties and five difficulty levels. For benchmarking purposes, we assessed the performance of eight state-of-the-art open-source and proprietary models, such as GPT-5, Gemini 2.0 Flash, and Claude 4-Sonnet. Our findings highlight the need for further domain-specific enhancements. We release the dataset and evaluation scripts to broaden the diversity of medical data benchmarks, expand the scope of evaluation suites for LLMs, and enhance the multilingual capabilities of models for deployment in clinical settings. --- ### Optimizing Prompts for Large Language Models: A Causal Approach Authors: Wei Chen, Yanbin Fang, Shuran Fu, Fasheng Xu, Xuan Wei Published: 2026-02-02 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.01711v1 Large Language Models (LLMs) are increasingly embedded in enterprise workflows, yet their performance remains highly sensitive to prompt design. Automatic Prompt Optimization (APO) seeks to mitigate this instability, but existing approaches face two persistent challenges. First, commonly used prompt strategies rely on static instructions that perform well on average but fail to adapt to heterogeneous queries. Second, more dynamic approaches depend on offline reward models that are fundamentally correlational, confounding prompt effectiveness with query characteristics. We propose Causal Prompt Optimization (CPO), a framework that reframes prompt design as a problem of causal estimation. CPO operates in two stages. First, it learns an offline causal reward model by applying Double Machine Learning (DML) to semantic embeddings of prompts and queries, isolating the causal effect of prompt variations from confounding query attributes. Second, it utilizes this unbiased reward signal to guide a resource-efficient search for query-specific prompts without relying on costly online evaluation. We evaluate CPO across benchmarks in mathematical reasoning, visualization, and data analytics. CPO consistently outperforms human-engineered prompts and state-of-the-art automated optimizers. The gains are driven primarily by improved robustness on hard queries, where existing methods tend to deteriorate. Beyond performance, CPO fundamentally reshapes the economics of prompt optimization: by shifting evaluation from real-time model execution to an offline causal model, it enables high-precision, per-query customization at a fraction of the inference cost required by online methods. Together, these results establish causal inference as a scalable foundation for reliable and cost-efficient prompt optimization in enterprise LLM deployments. --- ### Physics Informed Generative AI Enabling Labour Free Segmentation For Microscopy Analysis Authors: Salma Zahran, Zhou Ao, Zhengyang Zhang, Chen Chi, Chenchen Yuan, Yanming Wang Published: 2026-02-02 Categories: cs.CV, cond-mat.mtrl-sci, cs.AI arXiv: https://arxiv.org/abs/2602.01710v1 Semantic segmentation of microscopy images is a critical task for high-throughput materials characterisation, yet its automation is severely constrained by the prohibitive cost, subjectivity, and scarcity of expert-annotated data. While physics-based simulations offer a scalable alternative to manual labelling, models trained on such data historically fail to generalise due to a significant domain gap, lacking the complex textures, noise patterns, and imaging artefacts inherent to experimental data. This paper introduces a novel framework for labour-free segmentation that successfully bridges this simulation-to-reality gap. Our pipeline leverages phase-field simulations to generate an abundant source of microstructural morphologies with perfect, intrinsically-derived ground-truth masks. We then employ a Cycle-Consistent Generative Adversarial Network (CycleGAN) for unpaired image-to-image translation, transforming the clean simulations into a large-scale dataset of high-fidelity, realistic SEM images. A U-Net model, trained exclusively on this synthetic data, demonstrated remarkable generalisation when deployed on unseen experimental images, achieving a mean Boundary F1-Score of 0.90 and an Intersection over Union (IOU) of 0.88. Comprehensive validation using t-SNE feature-space projection and Shannon entropy analysis confirms that our synthetic images are statistically and featurally indistinguishable from the real data manifold. By completely decoupling model training from manual annotation, our generative framework transforms a data-scarce problem into one of data abundance, providing a robust and fully automated solution to accelerate materials discovery and analysis. --- ### ARTIS: Agentic Risk-Aware Test-Time Scaling via Iterative Simulation Authors: Xingshan Zeng, Lingzhi Wang, Weiwen Liu, Liangyou Li, Yasheng Wang, Lifeng Shang, Xin Jiang, Qun Liu Published: 2026-02-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.01709v2 Current test-time scaling (TTS) techniques enhance large language model (LLM) performance by allocating additional computation at inference time, yet they remain insufficient for agentic settings, where actions directly interact with external environments and their effects can be irreversible and costly. We propose ARTIS, Agentic Risk-Aware Test-Time Scaling via Iterative Simulation, a framework that decouples exploration from commitment by enabling test-time exploration through simulated interactions prior to real-world execution. This design allows extending inference-time computation to improve action-level reliability and robustness without incurring environmental risk. We further show that naive LLM-based simulators struggle to capture rare but high-impact failure modes, substantially limiting their effectiveness for agentic decision making. To address this limitation, we introduce a risk-aware tool simulator that emphasizes fidelity on failure-inducing actions via targeted data generation and rebalanced training. Experiments on multi-turn and multi-step agentic benchmarks demonstrate that iterative simulation substantially improves agent reliability, and that risk-aware simulation is essential for consistently realizing these gains across models and tasks. --- ### Game of Thought: Robust Information Seeking with Large Language Models Using Game Theory Authors: Langyuan Cui, Chun Kai Ling, Hwee Tou Ng Published: 2026-02-02 Categories: cs.CL, cs.AI, cs.GT arXiv: https://arxiv.org/abs/2602.01708v1 Large Language Models (LLMs) are increasingly deployed in real-world scenarios where they may lack sufficient information to complete a given task. In such settings, the ability to actively seek out missing information becomes a critical capability. Existing approaches to enhancing this ability often rely on simplifying assumptions that degrade \textit{worst-case} performance. This is an issue with serious implications in high-stakes applications. In this work, we use the game of Twenty Questions to evaluate the information-seeking ability of LLMs. We introduce and formalize its adversarial counterpart, the Strategic Language Search (SLS) problem along with its variants as a two-player zero-sum extensive form game. We propose Game of Thought (GoT), a framework that applies game-theoretic techniques to approximate a Nash equilibrium (NE) strategy for the restricted variant of the game. Empirical results demonstrate that our approach consistently improves worst-case performance compared to (1) direct prompting-based methods and (2) heuristic-guided search methods across all tested settings. --- ### LaDi-RL: Latent Diffusion Reasoning Prevents Entropy Collapse in Reinforcement Learning Authors: Haoqiang Kang, Yizhe Zhang, Nikki Lijing Kuang, Yi-An Ma, Lianhui Qin Published: 2026-02-02 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.01705v3 Reinforcement learning has become a central paradigm for improving LLM reasoning, but most existing methods optimize policies over discrete token sequences. This creates a mismatch between the optimization space and the structure of reasoning: many important decisions are semantic, global, and trajectory-level rather than local token choices. Continuous latent-space RL offers a promising alternative by allowing policies to explore higher-level reasoning representations. However, simply moving to latent space is not sufficient. The resulting policy must model a complex, multi-modal distribution over valid reasoning trajectories. We therefore propose Latent Diffusion Reasoning with Reinforcement Learning (LaDi-RL), where a diffusion model generates latent reasoning trajectories through iterative denoising. This formulation enables structured exploration and expressive distribution modeling, but also introduces a fundamental credit-assignment challenge: the policy acts in latent space, while rewards are observed only after the latent is decoded into text. A naive rollout strategy therefore entangles latent reasoning quality with text decoding quality, making it unclear whether an incorrect answer results from a poor latent trajectory or from an imperfect textual realization. To address this, we introduce hierarchical latent-text rollouts. We sample multiple text completions for each latent trajectory and aggregate their rewards to obtain a decoder-marginalized estimate of latent utility. This provides a cleaner and lower-variance reward signal for optimizing the diffusion policy. Empirically, LaDi-RL outperforms token-level RL by 9.4% on code generation and 5.7% on math reasoning in pass@1, and even surpasses the base model's pass@k performance. --- ### $\textbf{AGT$^{AO}$}$: Robust and Stabilized LLM Unlearning via Adversarial Gating Training with Adaptive Orthogonality Authors: Pengyu Li, Lingling Zhang, Zhitao Gao, Yanrui Wu, Yuxuan Dong, Huan Liu, Bifan Wei, Jun Liu Published: 2026-02-02 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2602.01703v1 While Large Language Models (LLMs) have achieved remarkable capabilities, they unintentionally memorize sensitive data, posing critical privacy and security risks. Machine unlearning is pivotal for mitigating these risks, yet existing paradigms face a fundamental dilemma: aggressive unlearning often induces catastrophic forgetting that degrades model utility, whereas conservative strategies risk superficial forgetting, leaving models vulnerable to adversarial recovery. To address this trade-off, we propose $\textbf{AGT$^{AO}$}$ (Adversarial Gating Training with Adaptive Orthogonality), a unified framework designed to reconcile robust erasure with utility preservation. Specifically, our approach introduces $\textbf{Adaptive Orthogonality (AO)}$ to dynamically mitigate geometric gradient conflicts between forgetting and retention objectives, thereby minimizing unintended knowledge degradation. Concurrently, $\textbf{Adversarial Gating Training (AGT)}$ formulates unlearning as a latent-space min-max game, employing a curriculum-based gating mechanism to simulate and counter internal recovery attempts. Extensive experiments demonstrate that $\textbf{AGT$^{AO}$}$ achieves a superior trade-off between unlearning efficacy (KUR $\approx$ 0.01) and model utility (MMLU 58.30). Code is available at https://github.com/TiezMind/AGT-unlearning. --- ### Beyond Single-Modal Analytics: A Framework for Integrating Heterogeneous LLM-Based Query Systems for Multi-Modal Data Authors: Ruyu Li, Tinghui Zhang, Haodi Ma, Daisy Zhe Wang, Yifan Wang Published: 2026-02-02 Categories: cs.DB, cs.AI arXiv: https://arxiv.org/abs/2602.01701v2 With the increasing use of multi-modal data, semantic query has become more and more demanded in data management systems, which is an important way to access and analyze multi-modal data. As unstructured data, most information of multi-modal data (text, image, video, etc.) hides in the semantics, which cannot be accessed by traditional database queries like SQL. Given the power of Large Language Models (LLMs) in understanding semantics and processing natural language, in recent years several LLM-based semantic query systems have been proposed to support semantic querying over unstructured data. However, this rapid growth has produced a fragmented ecosystem. Applications face significant integration challenges due to (1) disparate APIs of different semantic query systems and (2) a fundamental trade-off between specialization and generality. Many semantic query systems are highly specialized, offering state-of-the-art performance within a single modality but struggling with multi-modal data. Conversely, some "all-in-one" systems handle multiple modalities but often exhibit suboptimal performance compared to their specialized counterparts in specific modalities. This paper introduces Meta Engine, a novel ``query system on query systems'', designed to resolve those aforementioned challenges. Meta Engine is a unified semantic query engine that integrates heterogeneous, specialized LLM-based query systems. Its architecture comprises five key components: (1) a Natural Language (NL) Query Parser, (2) an Operator Generator, (3) a Query Router, (4) a set of Adapters, and (5) a Result Aggregator. In the evaluation, Meta Engine consistently outperforms all baselines, yielding 3--6x higher F1 in most cases and up to ~24x on specific datasets. --- ### Mitigating loss of control in advanced AI systems through instrumental goal trajectories Authors: Willem Fourie Published: 2026-02-02 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2602.01699v1 Researchers at artificial intelligence labs and universities are concerned that highly capable artificial intelligence (AI) systems may erode human control by pursuing instrumental goals. Existing mitigations remain largely technical and system-centric: tracking capability in advanced systems, shaping behaviour through methods such as reinforcement learning from human feedback, and designing systems to be corrigible and interruptible. Here we develop instrumental goal trajectories to expand these options beyond the model. Gaining capability typically depends on access to additional technical resources, such as compute, storage, data and adjacent services, which in turn requires access to monetary resources. In organisations, these resources can be obtained through three organisational pathways. We label these pathways the procurement, governance and finance instrumental goal trajectories (IGTs). Each IGT produces a trail of organisational artefacts that can be monitored and used as intervention points when a systems capabilities or behaviour exceed acceptable thresholds. In this way, IGTs offer concrete avenues for defining capability levels and for broadening how corrigibility and interruptibility are implemented, shifting attention from model properties alone to the organisational systems that enable them. ---