Research

Open problems for this view are being prepared; they appear within a day.

• arXiv cs.AISep 29

  Learning to Prove, Not Just to Answer: Reinforcement Learning from Formal Verification for Natural-Language Logical Reasoning

  Qili Zhang, Qianren Mao, Hanze Cai, Kaiming Zhao, Yuening He +9

  Large language models (LLMs) are increasingly deployed for natural-language logical reasoning, where the final answer is easy to check but the proof behind it is not. In natural-language logical reasoning, an intermediate conclusion should follow from its premises, and the resulting derivation should support the final answer. Existing methods lack machine-checkable verification of intermediate conclusions and answer-supporting proof dependencies, so they may assign credit to invalid or answer-irrelevant steps. We propose Proof-R1, an RL framework from formal verification that trains LLMs to construct verifiable proofs for natural-language logical reasoning. Proof-R1 admits a generated conclusion into the verified proof state only when the corresponding reasoning action satisfies the proof obligations through UNSAT-based machine-checkable formal verification. Proof-R1 also recovers the answer-supporting dependency closure to trace the proof structure of the final answer and align outcome credit with the proof dependencies. Experiments demonstrate that Proof-R1 improves answer accuracy across three logical reasoning benchmarks and four backbone models and outperforms training-free…

  PDF

  Summarize this
• arXiv physics.flu-dynSep 29

  Probabilistic Symbolic-Distillation Model of Droplet Collision for Spray Simulation at High Ambient Pressures

  Weiming Xu, Tao Yang, Peng Zhang

  Droplet collision governs droplet population dynamics in many chemical engineering processes, such as spray drying, spray cooling, agricultural spraying, and combustion. Existing analytical models impose deterministic, pairwise boundaries between collision outcomes, whereas machine-learning classifiers lack the explicit functional form required of analytical collision submodels. In this study, we develop a probabilistic symbolic-distillation model using nearly forty thousand experimental events spanning eight regimes and five dimensionless parameters, including over five thousand data for ambient pressure up to 50 atm. A machine-learning teacher learns the joint outcome-probability landscape from these data, and symbolic regression subsequently distils it into eight class-specific expressions that jointly define a coupled analytical model. The resulting analytical field replaces abrupt regime switching with finite-width fuzzy boundaries. It outperforms the evaluated conventional analytical boundary models and reveals that their main limitation is the inability of zero-width boundaries to represent gradual probability transitions. The "biased-dice" sampling scheme provides a…

  PDF

  Summarize this
• arXiv cs.CVSep 29

  Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL

  Songlin Yang, Xiaotong Zhao, Jiacheng Zhang, Zhe Wang, Toyota Li +3

  Multi-reward guided reinforcement learning (i.e., RL) offers a promising way to improve joint audio-video diffusion models along several complementary objectives, including modality-specific quality, cross-modal semantic alignment, and temporal synchronization. Its effectiveness, however, depends on two quantities that change during training: where reward-driven updates should act, and how competing rewards should be combined. Existing methods tend to rely on fixed routing and reward weights, failing to track evolving model functions. To address these limitations, we propose Adaptive Reward Routing to jointly adapt update locations and reward coordination during forward-process RL (i.e., DiffusionNFT) of joint audio-video diffusion models. Our method consists of two components. (i) Cross-Modal Influence-Guided Routing (Localizing Updates): We use bidirectional cross-attention responses as an efficient proxy for evolving cross-modal influence, dynamically reweighting token-aware losses and scaling gradients across cross-modal layers without additional model interventions. (ii) Preference-Preserving Modality-Aware Reweighting (Coordinating Rewards): We preserve predefined weights…

  PDF

  Summarize this
• arXiv cs.AISep 29

  V-Engram: Trigger-Indexed External Memory for Modular Text-to-Image Personalization

  Haoran He, Runyuan Cai, Yiming Wang, Lin Yu, Xiaodong Zeng

  Pretrained text-to-image models contain broad visual knowledge, yet they cannot reliably acquire or refine a specific visual identity from only a few references while preserving compositional control. Token-embedding methods are compact but often underfit identity, whereas adapter-based methods improve fidelity through persistent weight updates that can be costly to store and interfere when concepts are composed. We introduce V-Engram, a trigger-indexed external memory mechanism for Stable Diffusion 3.5. Each concept is assigned an explicit trigger that retrieves concept-specific memory, whose gated directions enter frozen text-encoder and MMDiT context states as relative residuals. Separating this memory from backbone adaptation enables prompt-selective and multi-concept access without merging model updates. Experiments show that V-Engram broadly matches DreamBooth-LoRA in overall subject fidelity while showing advantages in settings such as contextual subject preservation. Prompt-matched loading retrieves only matched entries, reducing most additional adaptation-state loading for a single-concept query. Qualitative results further demonstrate paired-trigger composition and…

  PDF

  Summarize this
• arXiv cs.CRSep 29

  ToolFence: Fine-Grained Authorization for Secure Tool-Using LLM Agents

  Yanjie Li, Xiangyu He, Xuelong Dai, Bin Xiao

  Tool-using LLM agents remain vulnerable to indirect prompt injection because trusted instructions and untrusted observations share one context, allowing malicious content to steer consequential input-filtering defenses. Multi-path consensus defenses still leave a high attack success rate because they examine content or aggregated outputs rather than authorizing effects, especially for the within-tool attack, which preserves the intended tool but manipulates its arguments. Data-Flow Control such as CaMeL provides stronger guarantees, but incurs substantial time latency that limits practical deployment. We introduce ToolFence, which compiles a typed authorization blueprint before execution, enforces it through a deterministic monitor, and when the blueprint is incomplete asks a judge to grant new capabilities rather than adjudicate each concrete call. ToolFence provides two key advantages. First, its fine-grained provenance-aware authorization enables the system to distinguish user-authorized values from untrusted observations, effectively addressing the within-tool attack. Second, its deterministic fast path and capability-level runtime grants substantially reduce the frequency of…

  PDF

  Summarize this
• arXiv cs.CVMultimodalSep 29

  Exploring In-Context Learning for Handwritten Text Recognition

  Eric Ayllon, Abel Gandia, Jorge Calvo-Zaragoza

  Handwritten Text Recognition (HTR) systems have become an indispensable tool for the digitization of historical documents. Not only do they cut down time and cost, but they also allow democratizing access and processing of their contents by generating their transcripts. However, literature in HTR currently focuses mostly on specialized models that require large amounts of annotated samples to achieve satisfactory performance. We explore the use of In-Context Learning with pre-trained Vision-Language Models (VLMs) to create a transcription pipeline without updating the model's parameters. We then evaluate this pipeline across multiple collections and models, and demonstrate that general-purpose VLMs can be effectively taught how to transcribe handwritten text from images. To assess how our observations may translate to practical applications, we evaluate the performance in a Cross-Domain (CD) scenario, where context examples are drawn from a different collection than the query image. Results in both the controlled In-Domain (ID) scenario and the realistic CD scenario follow the same patterns. First, as context size grows, the error range is expected to narrow towards the average…

  AIEvals70PDF

  Summarize this
• arXiv cs.SDSep 29

  JoyAI-Voice 2.0: A Full-Continuous Autoregressive Speech Generation Model with Semantic-Acoustic Joint Representation

  Yafeng Chen, Boya Dong, Yankun Huang, Hao Li, Jingdong Li +15

  We present JoyAI-Voice~2.0, an end-to-end anthropomorphic speech generation model built upon a fully continuous, dual-encoder architecture. Raw speech is encoded into continuous latents and partitioned into patches. Each patch is decomposed by a semantic-acoustic dual encoder into a semantically purified representation and an acoustic representation, which are fused and jointly fed to a causal autoregressive Transformer for planning. The Transformer predicts the conditioning for the next patch, and a local diffusion Transformer renders its full latents for 48\,kHz synthesis. The model is trained with a joint flow-matching and stop-prediction objective, followed by supervised fine-tuning and reinforcement learning with DiffusionNFT to improve model performance. It achieves the lowest average word error rate of 2.51\% on Seed-TTS, a 14.9\% relative reduction over the strongest baseline, and state-of-the-art attribute fidelity on InstructTTSEval in both Chinese and English, leading on 5 of 10 perceptual dimensions with the highest overall score of 0.893 on MDVD-Eval.

  PDF

  Summarize this
• arXiv cs.CVSep 29

  HaPRL: Human-Anchored Process Reinforcement Learning for Visual Search Agent

  Zhangquan Chen, Yaoxin Niu, Xiang An, Mingze Sun, Zhumei Wang +3

  Multi-turn visual search agents answer questions about high-resolution images by iteratively deciding where to look. Reinforcement learning for these agents rewards only the final answer, leaving the search process unsupervised. Consequently, faulty routes in which the reasoning process is erroneous yet the final result is correct arise frequently, which in turn leads to ineffective training, i.e., scaling along the wrong paths. In this paper, we introduce HaPRL, the first framework to reinforce the search process with human search behavior. We first build an annotation platform and collect 1K+ human-annotated data with fine-grained behavioral signals. During training, a carefully designed judge scores each rollout with task-adaptive weights, anchored on the distilled trace of how a human annotator actually searched the same image. Extensive experiments show that HaPRL consistently outperforms outcome-based RL, and early-stage process supervision yields 6.7x more improvement in subsequent outcome-based scaling. Our results also demonstrate the importance of aligning model behavior with human process annotation signals, which offer new insight into the training of foundation models.

  PDF

  Summarize this
• arXiv cs.LGSep 29

  Corruption-Robust Sparse Linear Contextual Bandits with Knapsack Constraints

  Yige Wang, Hanyang Li, Yiming Zong, Wanteng Ma, Jiashuo Jiang

  We study sparse linear contextual bandits with knapsack constraints under joint reward and consumption corruption. Consumption corruption creates a challenge beyond corrupted rewards: it affects not only statistical estimates, but also the recorded budget, resource prices, and stopping decisions that govern future allocation. We develop Robust Optimistic Primal--Dual (ROPD), an estimator-modular framework that combines corruption-aware confidence widths with online resource prices and a budget-safety rule. With concrete sparse implementation, ROPD achieves regret against a clean population-LP benchmark of $\widetilde O(T^{2/3}+ΓT^{1/3})$ under forced exploration and population-design coverage, and $\widetilde O(\sqrt T+Γ)$ under on-policy realized-design coverage, for a supplied valid corruption bound $Γ$ under the stated proportional-budget scaling and fixed model/design parameters. When the corruption level is unknown, Shared-Grid adapts confidence radii around common point estimates fitted to a single realized history, incurring explicit initialization and master-comparison costs; its sharper on-policy guarantee additionally requires recommendation coverage. Both methods…

  AI10PDF

  Summarize this
• arXiv cs.CVSep 29

  InsightMap: Structured Spatial Modeling for Embodied Multimodal Reasoning

  Hongpei Zheng, Hujun Yin

  Language-guided navigation requires connecting partial observations to a persistent spatial reference and learning how actions change that representation. We introduce InsightMap, a framework that uses top-down maps as both explicit spatial memory and action-conditioned prediction targets. Historical views are linked to labeled map locations, and a shared multimodal backbone jointly learns navigation action prediction and post-action map generation. Map prediction provides auxiliary training supervision, while navigation inference decodes actions from the observed spatial context. An aligned RGB-D data pipeline supports a common interface for navigation, visual question answering, situated reasoning, and 3D grounding. On the validation-unseen splits of R2R-CE and RxR-CE, InsightMap achieves success rates (SR) of 56.9% and 54.9%, respectively. Adding map-prediction supervision improves R2R-CE SR by 4.3 and success weighted by path length (SPL) by 3.2 percentage points. On static spatial tasks, InsightMap achieves 103.7 CIDEr on ScanQA, 60.1% exact-match accuracy on SQA3D, and 53.1% grounding accuracy at 0.5 IoU on ScanRefer with detected object proposals. On Unitree Go2, it…

  PDF

  Summarize this
• arXiv cs.AISep 29

  Accelerated surrogate dynamics for dynamical, stochastic system evolution

  Marco Jochum, Ioannis Kouroudis, Gohar Ali Siddiqui, Taher Amine Hamzaoui, Manuel Gößwein +1

  Dynamic simulations are an entrenched way of gaining insight into the evolution of system dynamics. Their computational cost however is often prohibitively high, especially in cases of stochastic frameworks. Machine learning algorithms are especially suited as simulation surrogates. Nevertheless, they face some very distinct limitations. Firstly, the sheer dimensionality of these systems, however, precludes the use of traditional time series models who struggle with high dimensional feature spaces. Additionally, traditional time series focus exclusively on either long or short range effects, causing local or global drift given enough time. In this paper, we propose a framework that addresses those limitations. Our framework combines a Variational Autoencoder, with a convolutional or graph basis that reduces the dimensionality of the system. This latent vector is propagated in time using a Temporal Fusion Transformer model, which includes both long range and short range effect encoding, as well as static covariate support. We test our framework on three distinct cases, to prove its robustness and in all three we have achieved practically identical to the simulation results at a…

  PDF

  Summarize this
• arXiv cs.ROSep 29

  EgoHumanoid-V2: Human-to-Humanoid Transfer of Coordinated Whole-Body Skills for Loco-Manipulation

  Jin Chen, Yiming Jiang, Chongyang Xu, Modi Shi, Shijia Peng +6

  Human demonstrations capture diverse scenes and rich whole-body skills without requiring robot teleoperation. Prior work on egocentric transfer has emphasized scene generalization in loco-manipulation under decoupled control, leaving direct transfer of coordinated whole-body skills less explored. We present EgoHumanoid-V2, the first egocentric human-to-humanoid skill transfer framework for coordinated whole-body loco-manipulation. At its core, coarse-to-fine action alignment combines kinematic reference correction with dynamics-aware refinement. It improves end-effector pose accuracy while preserving whole-body coordination. We also use robot-arm rendering and training-time image augmentation to reduce the visual embodiment gap and improve viewpoint robustness. On four real-world tasks, vision-language-action (VLA) policies trained on aligned human data show zero-shot skill transfer without target-task robot demonstrations. Task scores are comparable to those of policies trained on teleoperation data at a lower collection cost. These results support human data as direct skill supervision.

  Code
• arXiv cs.CVSep 29

  Sparse cubical complexes for efficient topology-preservation in image data

  Alexander H. Berger, Marco Fontana, Daniel Rueckert, Johannes C. Paetzold, Laurin Lux +1

  Persistent homology (PH) is a frequently used tool for extracting and preserving topological information from image data, particularly in image segmentation, where preservation of topological structures is important. However, despite its general applicability across dimensionality, domains, and target structures, the runtime cost of PH-based methods often makes their practical use infeasible. In this work, we argue that this runtime cost is largely driven by processing information that is unimportant for downstream application (e.g. as optimization objective). We propose sparse cubical filtrations as an alternative foundation for PH computation, reducing subsequent computational costs by factors of up to 100 on real datasets. We show close agreement with the optimization signal of the dense counterpart and empirically evaluate our solution's effectiveness as an optimization objective in realistic training regimes where other PH-based objectives can practically not operate (i.e., 3D data with large patch sizes). We show how our solution improves topological accuracy by up to 80\% across six diverse datasets while maintaining pixel- and region-based accuracy.

  PDF

  Summarize this
• arXiv cs.AISep 29

  Absorbed in Inertia: Activation Analysis for Computer-Use Agents

  Giulio Segalini, Zhi Wen Soi, Jérémie Decouchant, Lydia Chen

  Computer-use agents have become increasingly capable of executing tasks on live desktops through natural-language instructions, based on trajectories of screenshots, actions, and reasoning. We discover that they can stealthily exhibit inertia, in which they repeat fruitless actions despite recognizing that these actions are ineffective. We hypothesize that inertia is reflected in the agent's internal state, i.e., the activation values of the agent's underlying model, and propose a protocol to measure the relationship between the two. Extensive analysis of high-dimensional activation states shows that inertia corresponds to an absorbing region of activation space, where activation values become stale across actions and even after attempts to steer them. We conjecture that drastically changing the agents' activations by re-initializing them is necessary to escape inertia. Specifically, we propose R$^3$ (Reset, Reroute, Restore), which temporarily resets the agent's context trajectory to escape the absorbing region and then restores the historical context to effectively complete the task. Our approach yields 17-55% lower measured inertia across models relative to unmodified agents.…

  PDF

  Summarize this
• arXiv cs.CLSep 29

  VLM Fine-Tuning for End-to-End Combinatorial Optimization

  Qingsong Yan, Xia Jiang, Yaoxin Wu, Wen Song, Lu Zhang +1

  Large language models (LLMs) have provided a unified interface for end-to-end combinatorial optimization (CO), but textual serialization alone may obscure spatial and relational structures that are important for generating effective CO solutions. This paper presents a general-purpose vision-language solver that augments textual instance descriptions with input-derived visual representations. A single vision-language model (VLM) is applied across different CO tasks and trained using supervised fine-tuning followed by verifier-guided reinforcement learning. While the visual inputs contain no gold solutions or solution-derived information, our experiments show that the VLM generally improves solution quality over its text-only counterpart, with particularly clear gains on more complex CO problems such as CVRP and JSSP. The advantage of visual information is more pronounced at large problem scales.

  PDF

  Summarize this
• arXiv cs.AISep 29

  SimpleEvol: An Agent-Loop Framework for LLM-Driven Automated Heuristic Design with Minimal Human Priors

  Jianghan Zhu, Cong Zhang, Rongjie Zhu, Chi Zhang, Zhiguang Cao

  Large language models (LLMs) have emerged as powerful tools for automated heuristic design (AHD), enabling iterative generation and refinement of heuristics. However, the dominant paradigm embeds LLMs as narrow, fixed components, such as crossover or mutation, within heavily hand-engineered evolutionary frameworks. We argue this misapprehends LLMs. It treats them as specialized tools rather than general reasoners, constrains them to low-level operations, and underutilizes their autonomy. Moreover, the extensive human priors in these frameworks violate the bitter lesson principle that general methods scaling with computation surpass hand-crafted solutions. This raises a key question: which AHD framework designs best convert stronger LLM capabilities into better heuristics? To address this, we propose metrics for LLM-driven AHD framework handcraftedness (AHI) and intelligence conversion efficiency (ICE). Evaluating ten LLMs across three challenging combinatorial optimization problems, we obtain a notable finding that frameworks with fewer human priors consistently yield higher ICE. Based on this finding, we propose SimpleEvol, an agent-loop framework for AHD which removes nearly…

  PDF

  Summarize this
• arXiv cs.CLSep 29

  Bridging Semantic Gaps in RAG through Generated Context Knowledge Fusion

  Xinkai Du, Chao Lv, Yalin Sun, Quanjie Han, Lei Yao +1

  Retrieval-Augmented Generation has established itself as a fundamental framework in natural language processing, seamlessly integrating information retrieval with the generative capabilities of large language models. However, this process is fundamentally constrained by a critical challenge: semantic space mismatch between queries and retrieved contexts. We propose Knowledge-Aware Semantic Bridging (KASB), a novel framework that improves passage selection quality through semantic space alignment between queries and retrieved documents through intelligent knowledge fusion. Our approach leverages the complementary strengths of generative and retrieval-based knowledge through a multistage process that enhances both relevance and accuracy. We evaluate KASB on three popular open-domain Question Answering datasets to demonstrate the effectiveness of our approach.

  PDF

  Summarize this
• arXiv cs.LGTraining & fine-tuningSep 29

  Interpolated Policy Distillation: A Controllable Continuum Between Off-Policy and On-Policy Distillation

  Youxu Shi, Yifan Sun, Dacheng Yin, Haomiao Tang, Guangting Wang +3

  Off-policy and on-policy distillation have traditionally been formulated as separate paradigms, each favoring a different property of distillation trajectories. Teacher-generated (off-policy) traces are typically high-quality but lie far from the student's distribution, whereas student-generated (on-policy) rollouts are more learnable but often contain erroneous reasoning. We view these paradigms as the endpoints of a policy continuum and posit that a more effective rollout policy may lie in between. We introduce \textbf{Interpolated Policy Distillation (IPD)}, which defines the next-token distribution at every decoding step as an explicit linear interpolation between the student and teacher distributions. The interpolation operates at the distribution level, token by token, and its coefficient provides direct control over the balance between trajectory quality and student learnability. Naively sampling from this policy would require sequentially querying the teacher at every token and is thus expensive. To make IPD practical, we accelerate it with a new speculative-decoding rule while exactly preserving the interpolated next-token distribution.At the trajectory level, the…

  AI70PDF

  Summarize this
• arXiv cs.LGSep 29

  Trajectory Soup: Pushing the Compute-Scaling Frontier of LLM Mid-training via Diverse Trajectories

  Zhehao Huang, Changxin Tian, Qingyuan Yang, Kunlong Chen, Ziqi Liu +3

  Mid-training equips pretrained large language models with specialized and reasoning capabilities, but the returns of this stage are bounded since additional serial compute yields little further downstream improvement and can even degrade some capabilities, which places a practical ceiling on how much compute mid-training absorbs. We revisit how this compute should be allocated to a single run or multiple similar optimizations. We find that branches forked from a shared checkpoint under various controlled recipe reaches measurably different regions of parameter space, and establish a form of compatible diversity that extending one run cannot supply. Therefore, we introduce Trajectory Soup, which distributes a mid-training budget over several independent branches, and consolidates strongest checkpoints selected on validation through intra- and inter-trajectory averaging into a single model. A local bias and variance analysis separates the two averaging levels, showing that inter-trajectory averaging removes residual error beyond the reach of averaging within a trajectory, while checkpoint selection carries a bias that bounds how many checkpoints are worth merging. Across model…

  PDF

  Summarize this
• arXiv cs.ROSep 29

  Disentangling Spurious Correlations in Vision-Language-Action Models via Predicting Domain-Invariant Latent Lookahead

  Junghyun Kim, Ngseo Kim, ChungWoo Lee, Seoyeon Lee, Woo-Jeong Baek +5

  Vision-Language-Action (VLA) models remain brittle under visual distribution shifts, often relying on spurious correlations tied to domain-specific factors rather than task-relevant structure. We propose Domain-Invariant Latent Lookahead (DILL), a representation-learning framework that mitigates shortcut learning in VLA policies. Our key idea is to supervise policies with domain-invariant future latents learned from domain-transformed trajectory data. A Task-Domain Encoder is trained with contrastive objectives and Gaussian disentanglement regularization to separate task-relevant structure from domain-specific visual variation. The learned encoder then provides future latents for VLA policy learning through lookahead prediction and domain disentanglement, encouraging the policy to focus on task-relevant structure rather than incidental visual factors. Counterfactual task-view evaluations show that DILL reduces shortcut reliance, while LIBERO-Plus evaluations demonstrate improved visual robustness, with 69.1% average success, 11.4 percentage points above the strongest baseline. Real-world manipulation experiments further support DILL's applicability beyond controlled simulation.…

  PDF

  Summarize this

• Character recognition OCR40+11.1%
• Quantum machine learning270.0%
• Spiking neural networks70.0%
• Voice AI62−12.7%
• Diffusion priors20−13.0%
• Channel state information15−25.0%
• Robotics149−27.0%
• Forecasting time102−29.2%