VLA 線 · 查看同日 AI 報告 →查看同日 AI 报告 →
VLA 研究日報 Pulsar
LIVE
— AI 線今日無資料 —— AI 线今日无资料 —
VLA 線VLA 线 · cs.RO · cs.AI · cs.LG

VLA 研究日報VLA 研究日报

共 44 篇

🔧 技術技术

📖 背景閱讀背景阅读

VLA [Tongji University]

Dreamer-SAC: Off-Policy Learning in Latent World Models for Sample-Efficient Autonomous Driving

Jiazhuo Li et al. · arXiv:2608.10386v1 Announce Type: cross Abstract: Sample-efficient reinforcement learning for autonomous driving is often limited by the trade-off between data efficiency and model bias. While world models reduce the reliance on costly environment interactions, policy optimization over learned dynamics remains sensitive to prediction errors. This paper proposes the Dreamer-SAC framework, which integrates a recurrent state-space world model with an off-policy soft actor-critic algorithm trained d

cs.RO 閱讀原文
VLA

XPolicyLab: A Unified Standard and Open Ecosystem for Robot Policy Evaluation and Deployment

XPolicyLab Community et al. · arXiv:2608.09892v2 Announce Type: replace Abstract: Robot policy evaluation and deployment remain fragmented by model-specific software dependencies, data representations, and runtime interfaces, so that connecting N policies to M evaluation environments requires O(NM) separate integrations. We present XPolicyLab, a unified standard and open ecosystem that reduces this cost to O(N+M). XPolicyLab specifies common observation, action, and trajectory schemas together with a minimal adapter interfac

cs.RO 閱讀原文
VLA [School of Computing and Information Technology, University of Wollongong]

CausalNav: Reliability-Certified Causal World Models for Control under Physical-Parameter Shift

Yiyao Zhang et al. · arXiv:2608.07809v1 Announce Type: new Abstract: A world model is only useful for physical AI if it changes what the agent does, and only safe if it declines to do so when it is wrong. We study both halves of that requirement with CausalNav, a controller built around a signed, action-conditioned transition graph over identified state coordinates. At deployment CausalNav simulates a small library of intervention sequences, converts their objective error into policy-logit advice, and admits that ad

cs.AI 閱讀原文
VLA [Sobey Media Intelligence Laboratory]

A Structural Dynamics Graph World Model: Unified Modeling, Constrained Rollout, and Interpretable Calibration

Wei Wang et al. · arXiv:2608.08689v1 Announce Type: new Abstract: The state evolution of a complex system arises jointly from object laws, relational propagation, domain conservation, and unmodeled error. Forcing all sources into one black box makes mechanism attribution and constraint preservation unauditable; forcing every mechanism into one equation family discards mature domain solvers. We propose SD-GWM, a Structural Dynamics Graph World Model as an executable structural contract: nodes declare self-dynamics

cs.AI 閱讀原文
VLA

verdi: retrieval is not transfer for continual world model optimization

Junyu Wu et al. · arXiv:2608.09537v1 Announce Type: new Abstract: Foundation world models have made remarkable progress in planning, simulation, and embodied intelligence. However, optimizing a pretrained world model toward a user-specified objective remains difficult: each campaign typically rediscovers optimization strategies from scratch, and the resulting knowledge rarely transfers to the next model. Existing research agents automate the optimization loop but treat successful strategies as directly reusable r

cs.AI 閱讀原文
VLA [Shenyang Pharmaceutical University]

Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models

Kevin Murphy · arXiv:2608.09696v2 Announce Type: new Abstract: Predicting the answer to interventional ``what if'' questions --- the outcome of an action never taken --- requires a \emph{mechanistic}, causal model, not a curve fit; and learning such a model requires \emph{experiments}, because passive data leaves its mechanisms unidentified. Experiments are expensive, so the central problem is \emph{data efficiency}. We present the Model Discovery Agent (MDA), which couples a large language model (LLM), used a

cs.AI 閱讀原文
VLA [DiDi International Business Group]

SpikeWorld: Fast-State Adaptation for Frozen Spiking World Models

Ziqiao Yu · arXiv:2608.07712v1 Announce Type: cross Abstract: A predictive model receives a self-supervised signal whenever the consequence of an action is observed. Using that signal after deployment is difficult when dynamics and semantics share parameters: freezing prevents adaptation, whereas weight updates require optimizer state and may alter the learned representation. Here we introduce SpikeWorld, a 1.45M-parameter sparse spiking model jointly trained for heterogeneous sensory prediction, semantics,

cs.AI 閱讀原文
VLA [Unit of Artificial Intelligence and Computer Systems, Department of Engineering, Università Campus Bio-Medico di Roma]

Compositional Cross-Modality Translation via Whole-Volume Multitask Latent Flow Matching

Daniele Molino et al. · arXiv:2608.08135v1 Announce Type: cross Abstract: Cross-modality medical image translation can reduce the burden of multi-modal acquisitions, yet the field remains constrained by two coupled limitations: methods operate on 2D slices or 3D patches rather than whole volumes, and train a separate model for each translation task. Both stem from a single cause, the absence of a sufficiently strong volumetric prior, which forces generative models to learn anatomical appearance and cross-modality mappi

cs.AI 閱讀原文
VLA [RhOS.ai]

Population-Scalable Multi-Agent World Modeling

Renjie Zhao et al. · arXiv:2608.08600v1 Announce Type: cross Abstract: World models have recently achieved impressive progress in visual prediction and interactive generation, but extending them to multi-agent environments introduces a fundamental scalability challenge. Existing methods generally assume a fixed number of agents during training and inference, which ties the model to a pre-determined agent population and limits inference-time scalability. Our key insight is that cross-view consistency should arise fro

cs.AI 閱讀原文
VLA [UC Davis]

Concept-Guided Spatial Regularization for World Models in Atari Pong

Yukuan Lu et al. · arXiv:2607.15142v2 Announce Type: replace Abstract: World models are usually evaluated as components of model-based reinforcement learning (MBRL) systems, leaving their standalone reliability understudied. We reproduce five visual world-model agents in Atari Pong -- DreamerV3, DIAMOND, TWISTER, Simulus, and STORM -- and match their reported agent performance. We then freeze the learned world models and evaluate them in two ways. In a closed-loop rollout diagnostic, a policy trained separately fr

cs.AI 閱讀原文
VLA [Shandong University]

Why Does the Future Branch? Identifiable Closure Tests for Stochastic Physical World Models

Yibin Dong · arXiv:2608.00591v2 Announce Type: replace Abstract: A calibrated stochastic world model can reveal how uncertain a future is without revealing why it branches. The same conditional future law can arise because an observation aliases physical states or because dynamics remain random after the declared full state is fixed. We prove that ordinary transitions cannot identify these two sources, even for a perfect probabilistic predictor. ClosurePairs makes them identifiable by crossing compatible mic

cs.AI 閱讀原文
VLA

Multilingual Agent-Based World Modeling for Social Science

Xuan Zhang et al. · arXiv:2512.07195v2 Announce Type: replace-cross Abstract: Multi-agent role-playing has recently shown promise for studying social behavior with language agents, but existing simulations are mostly monolingual without cross-lingual interaction, an essential property of real societies. We introduce MAWM, the first Multilingual Agent-based World Modeling framework that supports multi-turn multilingual interactions among generative agents with diverse sociolinguistic profiles. MAWM enables two modes

cs.AI 閱讀原文
VLA [Shandong University of Finance and Economics]

SIMMER: Benchmarking Latent Failures in LLM Executable Planning with a World Model

Xiaoxin Lu et al. · arXiv:2606.14574v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed as planners for autonomous agents in household environments. While existing benchmarks evaluate whether LLM-generated plans execute successfully, they overlook a critical type of failure: latent failures. Unlike immediate failures that trigger instant feedback at execution time and enable timely correction, latent failures do not immediately halt plan execution but silently compromise

cs.AI 閱讀原文
VLA

4D-WAM: 4D Consistent World Modeling for Autonomous Driving

Jiacheng Fu et al. · arXiv:2608.10107v1 Announce Type: new Abstract: Emerging World-Action Models (WAMs) have demonstrated promising performance in autonomous driving by jointly modeling future driving scene evolution and trajectory planning. However, existing WAMs are typically trained with video data, which is only 2D projections of the underlying 4D driving scene. Consequently, WAMs fail to understand and capture the structure of 4D scenes and thus generate visually plausible yet 4D inconsistent future prediction

cs.CV 閱讀原文
VLA

Flow Straight to Reality: Perceptually Consistent Flow Matching for Efficient Image Restoration

Sangwoo Jo et al. · arXiv:2608.10544v1 Announce Type: new Abstract: Image restoration is fundamentally constrained by the tradeoff between distortion and perception: minimizing pixel-wise error yields over-smoothed results, whereas optimizing for perceptual realism often introduces structural deviations. Recent approaches attempt to balance this tradeoff via posterior sampling or multi-stage generative pipelines, yet remain computationally expensive and architecturally complex. To overcome these limitations, we pro

cs.CV 閱讀原文
VLA [Beijing Haidian Hospital]

Sekai2: From World Exploration to Interactive World Modeling

Kang He et al. · arXiv:2608.09449v2 Announce Type: replace Abstract: Video world models must capture how scenes evolve over time and across viewpoints. Training them for long-horizon generation and camera control therefore benefits from long videos paired with camera trajectories and temporally grounded semantics. Existing corpora rarely offer the three together: large-scale web video provides broad visual diversity but no trajectories or time-aligned text, while pose-annotated datasets are typically short-range

cs.CV 閱讀原文
VLA

Meshy T2: Fast Native Mesh Generation with Flow Matching

Jiale Xu et al. · arXiv:2607.28675v2 Announce Type: replace-cross Abstract: Polygonal meshes are the standard surface representation of modern 3D pipelines, and generating high-quality meshes with artist-style topology is essential for film, gaming, and interactive 3D applications. Mainstream approaches serialize a mesh into a token sequence and decode it autoregressively, which is slow at inference and sensitive to error accumulation, making them impractical for interactive asset creation. We present Meshy T2, a

cs.CV 閱讀原文
VLA [Beijing Academy of Artificial Intelligence]

Order Matters in Retrosynthesis: Structure-aware Generation via Reaction-Center-Guided Discrete Flow Matching

Chenguang Wang et al. · arXiv:2602.13136v2 Announce Type: replace Abstract: Template-free retrosynthesis methods treat the task as black-box sequence generation, limiting learning efficiency, while semi-template approaches rely on rigid reaction libraries that constrain generalization. We address this gap with a key insight: atom ordering in neural representations matters. Building on this insight, we propose a structure-aware template-free framework that encodes the two-stage nature of chemical reactions as a position

cs.LG 閱讀原文
VLA

Where Flow Matching Leaks: Characterising Membership Signals Along the Interpolation Path

Thomas Sesmat et al. · arXiv:2606.07271v3 Announce Type: replace Abstract: Understanding memorization in generative models remains challenging, with implications for copyright and privacy. Beyond verbatim reproduction, models can encode subtler traces of their training data that never surface in their outputs yet remain exploitable. We refer to these measurable asymmetries as the \emph{membership signal}, and we study this regime for Flow Matching, which are increasingly used in deployed generative systems. We analyze

cs.LG 閱讀原文
VLA [Guangdong Polytechnic of Science and Technology]

Smooth Flow Matching for Synthesizing Functional Data

Jianbin Tan et al. · arXiv:2508.13831v4 Announce Type: replace-cross Abstract: Functional data, i.e., random functions observed over a continuous domain, are increasingly available in areas such as biomedical research, health informatics, and epidemiology. However, effective statistical analysis for functional data is often hindered by challenges such as privacy constraints, sparse and irregular sampling, infinite-dimensionality, and non-Gaussian structures. To address these challenges, we introduce a novel framewor

cs.LG 閱讀原文
VLA [Southwest Wisconsin Technical College]

Null-Space Flow Matching for MIMO Channel Estimation in Latency-Constrained Systems

Junjie Zhao et al. · arXiv:2604.22005v2 Announce Type: replace-cross Abstract: Accurate yet low-latency channel state information (CSI) acquisition is essential for multiple-input multiple-output (MIMO) communication systems. While advanced deep generative models, such as score-based and diffusion models, enable high-fidelity CSI reconstruction from limited pilot observations, they often suffer from high inference latency. To achieve accurate CSI estimation under stringent latency constraints, this paper proposes a

cs.LG 閱讀原文
首頁首页 / VLA 日報VLA 日报 / 2026-08-13