Research

• Reliable request execution in streaming video generation1 paper raises it · 0 address it

  Models often fail to follow incremental user requests while maintaining state consistency in real-time video generation.

  • StreamEval: Evaluating Interactive Streaming Video Generation Modelsraises
• Calibration and contrast-group accuracy in decision models1 paper raises it · 0 address it

  Aggregate accuracy hides failures on controlled variations and unreliable confidence estimates in decision-making systems.

  • DecisionPivot: A Diagnostic Benchmark for Decision Models in LLM Systemsraises
• Length generalization in state tracking1 paper raises it · 1 addresses it

  Models struggle to maintain accuracy on problems much longer than their training data without explicit progress alignment.

  • PAR: Progress-Aligned Recurrence for Length Generalization in State Trackingraises · addresses
• Token collapse in graph soft prompting1 paper raises it · 0 address it

  Graph-specific tokens lose discriminative power, reducing the method to a generic prompt with no graph information.

  • On the Token Collapse Phenomenon in Textual Graph Soft Promptingraises
• Coupled evaluation of multimodal agents and world models1 paper raises it · 0 address it

  Separate evaluation of agents and world models fails to predict success when they are combined in real-world tasks.

  • Dual Exam: Controlled Evaluation of Multimodal Agents and World Modelsraises

Named by an AI from these papers' abstracts.

• arXiv cs.CVOct 10

  TGuide: Faster Autoregressive Video Diffusion via Historical Trajectory Guidance

  Zhuo Chen, Bin Zou, Fanyue Wei, Lixin Duan, Angela Yao +1

  Can autoregressive video diffusion be accelerated further when only four denoising steps remain? Existing feature caching approaches struggle in this regime, as large feature changes between denoising timesteps undermine both direct reuse and lightweight predictors. We observe that features across video chunks remain strongly correlated at matching denoising timesteps, offering a complementary source of guidance. Building on this insight, we introduce TGuide, a framework that accelerates autoregressive video diffusion through a lightweight Anchor-Transport-Correct (ATC) predictor guided by historical sampling trajectories. Our ATC combines two complementary references: the current chunk's preceding-step features preserve its spatial structure, while the previous chunk's same-timestep features provide information at the target denoising stage. By integrating these references through spatial retrieval and adaptive correction, ATC improves velocity prediction accuracy despite the large gaps between denoising steps. To mitigate error accumulation across both denoising steps and video chunks, we train the predictor on its own autoregressive rollouts, allowing it to adapt to states…

  PDF

  Summarize this
• arXiv cs.CVOct 10

  Prospective Forcing: Learning to Look Ahead for Autoregressive Long Video Diffusion

  Yifan Shen, Yewei Xia, Gongxu Luo, Peiyuan Zhu, Boyang Sun +4

  Autoregressive video generators synthesize long videos through chunk-wise rollouts, yet they are typically trained to predict only the immediate future. This limited prediction horizon makes it challenging to maintain video quality over extended rollouts. To address this problem, we introduce Prospective Forcing, a multi-head prediction framework that injects long-range predictive signals into autoregressive video representations. Built on a rolling-window generator, Prospective Forcing attaches lightweight, offset-specific heads that share the same conditioning information and independently predict chunks at different future temporal offsets. By extending supervision beyond the next chunk, these heads encourage the shared history representation to retain information useful for longer-horizon prediction, supporting temporally consistent generation. At inference time, we accelerate sampling by using accepted future-chunk predictions to skip full-window backbone executions. We equip the head with learnable embeddings to generate multiple candidates for the next chunk, and a learned verifier either selects a candidate or rejects all and falls back to standard autoregressive…

  PDF

  Summarize this
• arXiv cs.CVOct 10

  TAG: Calibrating SAM3 for Universal Image Segmentation without Dense Supervision

  Hao Zhu, Heyu Sun, Shuo Jin, Jiayu Xiao, Feng Dai

  The recent Segment Anything Model 3 (SAM3) extends powerful promptable segmentation from spatial cues to concepts, raising the prospect of a single foundation model for universal image segmentation. However, this promise often fails to translate into reliable performance on downstream segmentation tasks. In this work, we empirically identify concept recognition, rather than mask quality, as the primary bottleneck: SAM3 accurately delineates the objects it recognizes yet struggles to robustly determine which concepts are present. Driven by this, we present \textit{\underline{T}ext \underline{A}nchor re-\underline{G}rounding (\TAG{})}, a simple yet effective framework that rectifies the concept recognition of SAM3 on the target domain without dense annotations. Specifically, \TAG{} introduces an \textit{Anchor Residual Pathway} comprising image-conditioned, low-rank adapters to re-ground text anchors in the target distribution and modulate subsequent text-conditioned interactions. Guided solely by image-level category labels, \TAG{} jointly optimizes binary cross-entropy with \textit{Soft Boundary Ranking} objectives to calibrate presence confidence and distinguish present concepts…

  PDF

  Summarize this
• arXiv cs.CVOct 10

  Can Synthetic UAV Benchmarks Be Trusted? Real-Synthetic Validation for UAV Model Selection

  Yuyi Zhi, Min Du, Bill Shi, Guodong Yuan, Junheng Liang +2

  Synthetic UAV imagery can expand pre-deployment test evidence when task-specific Real data are scarce, but visual plausibility or semantic label alignment alone does not establish validity for model selection. We study when Synthetic evaluation preserves the model-selection conclusions obtained from Real UAV data through two complementary cases under fixed evaluation protocols. In a requirement-specific road-debris benchmark, four language-conditioned perception systems obtain lower absolute F1 on Synthetic data, yet the point-estimate ordering and top-ranked model are preserved; bootstrap analysis yields no supported pairwise reversal, and size-matched resampling preserves the top-model decision. In contrast, a closed-set stress test on a separately materialized business corpus, using four VisDrone-compatible detectors over eight empirically supported classes, changes the point-estimate top-ranked detector and reverses three of six pairwise point-estimate preference directions. A complementary audit of five UAV business scenarios further reveals substantial Real-Synthetic mismatch in class composition, object density, and target scale, including systematic under-representation…

  PDF

  Summarize this
• arXiv cs.AIOct 10

  Shaping Latent Mixture-of-Experts: From Expert Geometry to Layerwise Capacity Allocation

  Yaoxiang Wang, Kai Zhang, Ruobing Xie, Lanrui Wang, Guoliang Zhao +2

  Fine-grained mixture-of-experts (MoE) models commonly increase expert count by narrowing each expert, treating expert shape as a by-product of routing granularity. LatentMoE moves expert computation into a lower-dimensional space, exposing the input dimension and intermediate width of each expert as explicit design choices. We show that an expert's local Jacobian rank is jointly bounded by these two dimensions, and that balancing them maximizes the rank ceiling at fixed per-expert parameters. Controlled shape sweeps across model scales and routing granularities consistently favor near-square experts. We further use layerwise intrinsic dimension (ID) to guide capacity allocation across depth, co-varying the number and shape of experts while keeping per-layer parameter count, activated FLOPs, and communication volume constant. Compared with layer-homogeneous baselines, our ID-guided allocation achieves lower validation loss and stronger downstream performance. These results establish expert shape and layerwise allocation as practical design axes for MoEs.

  PDF

  Summarize this
• arXiv cs.AIOct 10

  AegisVox: Factorized Privacy and Clinical Preservation for Long-Form Speech

  Praphul Singh, Akshat Agarwal, Ratul Ghosh, Aashna Kanuga, Devashish Khatwani +3

  Clinical speech reveals identity through both spoken identifiers and voice, yet its pauses, delivery, and speaker roles can also carry useful clinical evidence. Protecting that speech therefore requires more than preserving its words. We present AegisVox, a factorized framework that assigns consistent surrogate voices and edits identifier-bearing turns using document-consistent replacements. Across 390 public simulated or non-patient conversations totaling 63.6 hours, a matched comparison of two speech renderers separates replacement realization from retained identifiers, speaker linkage, and clinical preservation. Text-to-speech rendering realizes 535/601 planned replacements versus 453/601 for the codec-based speech editor. However, similar aggregate clinical preservation conceals more model-labeled contradictions, and conversation-wide speaker scores conceal greater edited-speech linkage under a score-direction sensitivity analysis. Fresh transcription of original audio provides a reference for interpreting the clinical measurement chain; an independent judge tests sensitivity to model-based assessment. Better replacement realization can therefore coexist with worse clinical…

  PDF

  Summarize this
• arXiv cs.AIOct 10

  PEARL: Process-Experience Aware Reinforcement Learning for Multi-Turn Agents

  Jie Yang, Mianqiu Huang, Yiwei Zhao, Bo Wang, Yang Liu +1

  Terminal rewards make multi-turn agents trainable without step-level annotations, but group-relative advantages provide little guidance about which intermediate decisions to adjust. Failed trajectories also contain reasonable actions, while unfavorable decision patterns can recur as training proceeds. We introduce PEARL (Process-Experience Aware Reinforcement Learning), which improves local credit assignment without an additional critic. Given two continuations from the same history with different outcomes, PEARL locates their first divergence and builds a feature representation of each branch's local decision. It clusters these decision features in recent failure and success memories to identify recurring local patterns. Using this pattern memory, PEARL selectively strengthens negative advantages at lower-reward decisions, while leaving positive advantages and the base policy optimizer unchanged. On AppWorld, PEARL improves over ARPO on Normal and Challenge tasks at both 4B and 8B scales. On ALFWorld, it achieves 97.9% mean success at 4B, 2.7 points above the strongest baseline, while remaining competitive at 8B. Ablations of shaping location, success-bank filtering, and memory…

  PDF

  Summarize this
• arXiv cs.CLOct 10

  PVFH-Bench: Benchmarking Premise-Induced Visual Fixation Hallucinations in Vision-Language Models

  Xinhao Wang, Junbo Cui, Zhenghao Liu, Yuan Yao, Xiaohua Li +2

  Large Vision-Language Models (LVLMs) have achieved remarkable progress across a wide range of multimodal tasks. However, object hallucination remains a persistent challenge, undermining model reliability in applications such as visual question answering, embodied agents, and human-AI decision support systems. In this paper, inspired by cognitive science studies on perceptual bias, we investigate a new failure mode termed Premise-Induced Visual Fixation Hallucination (PVFH). Specifically, PVFH refers to a premise-induced reasoning error in which models become anchored to visually confusable evidence, accept a false textual premise, and subsequently generate responses about an absent yet visually plausible object. To systematically study this phenomenon, we introduce PVFH-Bench, a benchmark that automatically constructs visually confusable but absent targets and pairs the core hallucination setting with diagnostic subsets to trace how models move from object recognition to Premise-Induced Visual Fixation Hallucination. Experimental results on 10 state-of-the-art LVLMs demonstrate that all evaluated models are highly vulnerable to Premise-Induced Visual Fixation Hallucination.…

  PDF

  Summarize this
• arXiv cs.CVOct 10

  Automatic assembly modeling through attention-based assembly feature mate prediction and assembly feature pattern recognition

  Ziheng Dai, Wanbin Pan, Zhihong Tang, Shuming Gao

  Assembly modeling plays an important role in constructing product models, yet it is still mainly performed via interactive operations that are experience-dependent and labor-intensive. Data-driven strategies hold promise for automating this process; however, existing approaches either predict poses that cannot directly generate editable B-Rep assembly constraints or require prescribed part pairs or predefined assembly faces. To reduce the large candidate space of constraint prediction without predefined assembly faces, we propose a data-driven framework based on assembly feature mate prediction. The framework performs automatic assembly modeling from unassembled B-Rep parts, using assembly features to group the geometric entities of local mating interfaces and restrict candidate formation. Given the lack of suitable assembly feature annotations in existing datasets, we construct a large-scale dataset through an automatic annotation pipeline. Using the annotated dataset, we train an attention-based network to predict assembly feature mates, with Engineering Compatibility Fusion (ECF) incorporating explicit engineering compatibility into learned matching scores. To improve the…

  PDF

  Summarize this
• arXiv cs.IROct 10

  The Company a Question Keeps: Auditing Open Jev-Style Models for Retrieval

  Jianbo Chen

  Jev's documented interface evaluates typed questions independently against shared evidence. We audit request independence in seven open Jev-style checkpoints on 276 constructed three-passage states from 92 TREC retrieval queries. Paired interventions separately change requested questions, displayed evidence, and candidate eligibility. Request expansion induces strict binary flips in 9.1%/8.0% of Nimble's judgments and changes 21.4%/18.9% of selection-or-abstention actions in TREC DL2019/2020 under a threshold of 0.5 fixed before inference. Correct-action rates change by 0.0/+8.2 percentage points, respectively, with 95% query-bootstrap intervals of [-6.0,6.0] and [3.8,12.6]. Field masking traces all 70 request-set flips to the schema fields serialized into each scoring prompt. In Von, fixing a shared separator's position eliminates two eligibility-induced preference flips in selected diagnostic states. Laya-typed's default CUDA path produces five passage swaps without strict binary flips, and both yearly action-change intervals include zero; in an FP32 rerun, its probability movement vanishes at the model's four-decimal reporting resolution.

  PDF

  Summarize this
• arXiv cs.CVOct 10

  DuSRFlow: Dual-Lens Super-Resolution via Parallax-Aware Flow Estimation and Complementary Reference Warping

  Fangpu Zhang, Huanjing Yue, Zifan Cui, Shaoxiong Tu, Qirui Yang +1

  Dual-lens super-resolution (DuSR) aims to enhance a wide-angle low-resolution (LR) image by exploiting a telephoto reference (Ref) image. A central challenge in DuSR is reliable reference utilization under large parallax, occlusion, and cross-camera imaging discrepancies. Existing methods often employ off-the-shelf monocular optical flow models to provide geometric priors. However, their assumptions of photometric consistency and smooth motion are violated in dual-lens scenarios, leading to unreliable alignment and degraded reference-based reconstruction. To address these issues, we propose DuSRFlow, a dual-lens super-resolution framework that improves reference utilization from both correspondence learning and reference aggregation. First, we introduce DuFlowNet, a dedicated dual-lens flow estimator for robust cross-view alignment. To train DuFlowNet without ground-truth flow annotations, we develop a real--synthetic data fusion strategy that composites synthetic foreground objects onto real dual-lens image pairs, generating controllable large-parallax samples while preserving realistic cross-camera imaging characteristics. Second, we observe that reference reliability is highly…

  PDF

  Summarize this
• arXiv cs.LGOct 10

  TagBO: LLM-Driven Task-Aware Graph Bayesian Optimization for Scientific Discovery

  Xinzhe Yuan, Zimu Zeng, Zhuo Chen, Jianshu Zhang, Jinzong Dong +4

  Mixed-variable optimization in scientific discovery often requires exploring large combinatorial spaces under costly experimental evaluations, making sample?efficient Bayesian optimization (BO) essential. However, existing BO methods typ?ically rely on structural descriptors to define similarity among categorical variables, implicitly assuming that structural similarity reflects similarity in task performance. In scientific optimization, this assumption is often violated, leading to surrogate representations that are poorly aligned with the optimization objective. To address this limitation, we propose TagBO (Task-aware Graph Bayesian Optimization), a method that integrates LLM-derived relational priors with descriptor-based struc?tural information for mixed-variable Bayesian optimization. Rather than directly using LLM outputs as predictive scores, TagBO treats LLM outputs as a potentially noisy source of task-aware relational priors and extracts coarse ordinal relational signals from LLM reasoning to construct task-aware similarity structures for scien?tific optimization. TagBO then performs constrained Gaussian process Bayesian optimization over the resulting joint…

  PDF

  Summarize this
• arXiv cs.AIOct 10

  From Existing Methods to New Research Ideas: Two Perspectives on Recursive Self-Improvement

  Leijun Zhou, Yanke Yu, Zhihao Liu, Qu Xiang, Tiancheng Hu +8

  Recursive self-improvement (RSI) offers a route to AI systems that participate in their own continued development. Recent methods allow language agents to retain changes to their parameters, memory, skills, and code for subsequent execution and improvement. We examine how these methods can inform new research ideas through two complementary perspectives. First, we introduce a unified taxonomy with nine design dimensions organized into four groups: update targets, update organization, update schedule and scope, feedback and selection. This taxonomy places existing methods in a shared design space, where examining individual dimensions and their interactions can inspire new research ideas. Second, we examine how existing RSI methods draw on traditional deep learning, for example through optimization, regularization, data augmentation, continual learning, and adversarial learning. We develop further ideas by examining more specific learning mechanisms and drawing on evolutionary computation. We also review how existing benchmarks assess self-improvement under online, offline, and offline-to-online settings. Together, these perspectives help researchers develop new RSI research ideas…

  PDF

  Summarize this
• arXiv cs.CVOct 10

  EarthAlign: Learning Language-Aligned Representations of Earth System Data

  Fadillah Adamsyah Maani, Numan Saeed, Jiaqi Ma, Dat Tien Nguyen, Youssef Wehbe +2

  Interpreting Earth system conditions is central to understanding environmental risks and informing decisions across weather- and climate-sensitive sectors. Existing multimodal weather systems primarily target task-specific prediction, generation, or question answering, while general-purpose alignment between Earth system data and language remains underexplored due to the limited availability of diverse language supervision grounded in meteorological conditions. To fill this gap, we introduce EarthAlign, a large-scale dataset with broad geographic coverage spanning 2000-2024 that combines 10 expert-curated natural event and disaster data sources with climatology-derived normal-weather samples. Each sample includes temporal and geospatial information and four grounded caption styles aligned with 63-variable ERA5 meteorological data. Building on EarthAlign, we introduce MeteoLIP, a dual-encoder framework for learning aligned meteorology-language representations. MeteoLIP incorporates MetTok, which uses a geolocation- and time-conditioned query to aggregate variable-specific patch embeddings into a compact sequence of meteorology tokens. To comprehensively assess Earth system…

  PDF

  Summarize this
• arXiv cs.LGOct 10

  From Rainfall to Road-Network Functionality: Transferable Graph Forecasting for Flood-Disrupted Transportation Networks

  Junyan Wang, Naiyu Wang

  Extreme rainfall can rapidly degrade road-network functionality (RNF), disrupting emergency mobility, accessibility, evacuation, logistics, and infrastructure restoration. Existing flood-transportation impact models are often difficult to deploy across regions because they rely on local calibration, intensive simulation workflows or target-region retraining. This study proposes G-R2R, a transferable spatiotemporal graph-learning framework that reframes rainfall-induced road-network disruption as a region-conditioned, topology-flexible graph forecasting problem for unseen transportation networks. The framework integrates ego-centered subgraph sampling, terrain-conditioned graph representation, region-conditioned dual-level static encoding, and dynamic rainfall-network feature learning. Static geographic and infrastructure attributes are fused with rainfall forcing and recent RNF states to forecast node-level RNF across heterogeneous road networks. G-R2R is evaluated using simulation-derived RNF sequences from ten flood-prone regions in Wenzhou, China, under unseen-region testing protocols. It outperforms representative forecasting baselines, achieving a stabilized MAPE of 2.33%…

  PDF

  Summarize this
• arXiv cs.ITOct 10

  Limitations on Autoregressive Token Generation via Sequential Sampling

  Gal Arnon, Andrej Bogdanov, Paul Lou, Giulio Malavolta, Alon Rosen +1

  We study autoregressive token generation through the notion of sequential samplers: A circuit that samples the next symbol only given the previous ones and possibly a small amount of state. We show that (1) a sequential sampler with $k$ bits of state can be simulated by a stateless one at a roughly $O(2^{k})$ size overhead; (2) efficient insertional sampling (Stern, Chan, Kiros, Uszkoreit, ICML 2019) is more powerful than efficient sequential sampling in any fixed order; (3) sequential samplers with small state cannot establish certain forms of covert cryptographic channels. Result (1), together with the pseudoentropy vs. sequential sampleability duality of Vadhan and Zheng (STOC 2012), characterizes efficient sequential sampleability with small state. Result (3) provides a potential safety mechanism against subliminal coordination among malicious LLM agents.

  PDF

  Summarize this
• arXiv cs.LGOct 10

  LLM-Augmented Bayesian Optimization with Adaptive Policies for Chiplet Design Space Exploration

  Hang Liu, Zhengfei Chen, Zhengrui Chen, Hao Geng, Yu Li +1

  Chiplet technology is a key approach for extending Moore's Law. However, its design process is constrained by two primary challenges: the scarcity of early-stage platforms for rapidly evaluating chiplet-based heterogeneous systems, and the complex relationships between design parameters and optimization metrics. To address these challenges, we propose a synergistic framework that integrates a Large Language Model (LLM) with Bayesian Optimization (BO), enabling architectural-level simulation and automated optimization for the 2.5D/3D CPU-GPU heterogeneous chiplets. We extend the open-source chiplet simulator to evaluate 3D designs by supporting graph topologies. Further, to enhance the exploration efficiency of BO, we introduce an LLM that generates high-quality policies to guide the optimization process, enabled by our proposed adaptive directional policy reasoning (ADPR) and an exploration gain-aware fine-tuning method. Finally, we use the policy-guided BO to perform an automated and efficient exploration of the complex chiplet design space. Experiments on 2.5D and 3D chiplet reveal that our framework improves design space exploration efficiency.

  PDF

  Summarize this
• arXiv cs.CVOct 10▲ 58

  EviScene: Beyond "Is It AI?" for Agentic Image Factuality Assessment

  ZiAn Wang, Ruiqi Liu, Zhengbo Zhang, Yi Han, Jialiang Shen +8

  Determining whether an image is AI-generated does not establish whether the situation it depicts is factually supported. We formulate Image Factuality Assessment: given an image and a generic verification instruction, a system returns a supported or refuted verdict with an evidence-grounded explanation. Without a supplied textual claim, the system must progressively refine factual questions during investigation and align external evidence with the specific situation depicted. We introduce EviLens, an expert-reviewed benchmark of 10,174 supported and refuted images from controlled construction and web collection, covering twelve factual error types and evaluating both verdict accuracy and evidence sufficiency. We develop EviScene, a multimodal ReAct agent that interleaves visual inspection, external retrieval, and evidence analysis, using new findings to refine its questions and revisit relevant image details. We train a compact policy with supervised fine-tuning on reviewed teacher trajectories, followed by privileged on-policy self-distillation applied to verified decisions from the policy's own investigations. On the 1,527-image test set, the trained Qwen3.5-9B agent achieves…

  PDF

  Summarize this
• arXiv cs.AIOct 10

  Decoupling Knowledge Forgetting and Refusal Learning in MLLM Unlearning

  Haodong Chen, Shengtao Wen, Dong Liang, Lingbing Guo, Xiang Chen

  Current evaluations of multimodal unlearning typically focus on whether a model stops outputting target information. This surface-level criterion, however, masks two critical failure modes. First, knowledge suppression techniques often induce confabulation, leading the model to hallucinate facts about the unlearned subject. Second, refusal training merely alters observable behavior without erasing the underlying knowledge; such models might decline open queries but still identify correct answers under multiple-choice probing. To overcome these limitations, we propose Forget-Aware Self-Distillation (FASD). This method is designed to achieve honest ignorance, a state where the model genuinely loses the target knowledge and learns to acknowledge its absence. FASD separates these goals into two complementary channels. The behavior channel distills appropriate refusals from an ignorance-prompted copy of the model itself. Crucially, target tokens are masked from the teacher distribution to avoid accidentally reteaching the forgotten concepts. Simultaneously, the knowledge channel directly suppresses ground-truth answer spans independently of the model's generated responses. Experiments…

  PDF

  Summarize this
• arXiv cs.CVOct 10

  Bidirectional Adaptive Transformers for Multimodal Anomaly Detection

  Yuxin Jiang, Yunkang Cao, Weiming Shen

  The effective integration of features derived from RGB images and 3D point clouds presents a substantial challenge in the field of multimodal anomaly detection (MAD). Existing MAD methods typically rely on static fusion paradigms built upon frozen pre-trained encoders. While these frameworks facilitate spatial alignment, they lack the mechanism to establish latent semantic correspondence, thereby inducing cross-modal interference that degrades anomaly discriminability. To mitigate these limitations, this study proposes a Bidirectional Adaptive Transformers (BAT) framework, which constructs comprehensive and semantically aligned multimodal representations by leveraging complementary attributes across modalities. The BAT framework introduces a Bidirectional Feature Alignment (BFA) module, which employs a mutual predictive mechanism to bridge the gap between 2D textural patterns and 3D geometric structures. This bidirectional interaction explicitly enhances the textural granularity of point cloud descriptors while augmenting the spatial contextual awareness of RGB features. To ensure that the latent representations possess sufficient informational density for alignment, BAT…

  PDF

  Summarize this

• Anomaly detectors28+115.4%
• AI tutors15+36.4%
• Multimodal emotion8−11.1%
• Channel state information14−12.5%
• Electrocardiogram ecg34−15.0%
• Physics informed neural129−17.8%
• Forecasting time54−19.4%
• Medical image segmentation150−22.7%