Shanghai Jiao Tong University · 55 records

dateidtitleauthorsvenue↑
2026-11-192611.24408StrideWorld: Benchmarking Scene Rigidity and Action Consistency in Interactive Video World ModelChuang Wang et al.arXiv14
2026-11-172611.20986Calpha: Toward Native Biomolecular Intelligence in a General-Purpose Language ModelYong Liu et al.arXiv14
2026-11-13W4416236439Emergent long-tailed dynamics in spin iceChenyue Guo et al.Proceedings of the National Academy of Sciences
2026-11-102611.12870SWAM: Scaling World Action Models with Cross-Modal AlignmentYu Zhou et al.arXiv20
2026-11-042611.02017Switch-SWE: Do Coding Agents Hold Focus When Switching Between Unfinished Tasks?Shuochen Chang et al.arXiv9
2026-11-042611.03183Auto-Research Agent on MSA Organization to Improve Protein-Protein Complex Structure PredictionZilu Zhang et al.arXiv1
2026-11-032611.03092Avatar Intelligence: Amplifying Human Agency Through Persistent Personal AgentsZheng Wu et al.arXiv16
2026-10-29W4417000365Dynamo and Jet Interconnections in GRMHD Simulations of Black Hole Accretion DisksP. S. Santhiya et al.The Astrophysical Journal
2026-10-262610.35845Work Agents: Systems, Capabilities, and OptimizationZishan Xu et al.arXiv115
2026-10-222610.13177CompactSplat: Spatially Adaptive Gaussian Distribution for Feedforward Scene ReconstructionBing He et al.arXiv20
2026-10-222610.29317SpatialBrain: Spatial Intelligence Growing from ExperienceYifan Zhou et al.arXiv13
2026-10-202610.24520HABIT-Bench: Evaluating Habit Induction from Longitudinal Weak Evidence in Agent MemoryJunming Zhang et al.arXiv41
2026-10-192610.23787DLite: History-free Speculative Decoding for Agentic AIJiaming Xu et al.arXiv30
2026-10-192610.20019MorphAct: Robot Policies Morphing with the Worlds They Act InZiyan Liu et al.arXiv14
2026-10-162610.21359SWE-at-Scale: Scalable Issue Synthesis from Historical Bug FixesSilin Chen et al.arXiv20
2026-10-132610.13630Multi-Stream Attention ResidualsXiaohan Qin et al.arXiv51
2026-10-132609.35965Systematic Multi-Agent Vision-and-Language Navigation: Formulation, Benchmark, and MethodYunzhe Xu et al.arXiv10
2026-10-122610.12611SoftwareGym: Scaling Computer-Use Agent Training with Diverse Synthesized Software EnvironmentsTian Jin et al.arXiv86
2026-10-082609.33678SWE-Game: Can Coding Agents Build the Games We Want?Xiaoyu Chen et al.arXiv33
2026-10-012609.38334EVOKE: Eliciting World Knowledge in Agents for Transferable Decision-MakingYuhan Guo et al.arXiv36
2026-09-302609.37559APM-Bench: Benchmarking Cross-session Persistent Memory for Egocentric Streaming Video AssistantsJianguo Huang et al.arXiv36
2026-09-292609.35734GeoVerse: World-Consistent Novel View Synthesis in Geometric Latent SpaceKerui Ren et al.arXiv9
2026-09-292609.32353Fewer Tokens, More Self-Teaching: On-Policy Self-Distillation for Extreme Visual Token ReductionJunxian Li et al.arXiv8
2026-09-242609.27891Schrödinger's Code Repository: Have LLMs Learned SWE-bench or Memorized It?Silin Chen et al.arXiv28
2026-09-222609.24788Streaming Video Editing with Easy AdaptationYujia Hu et al.arXiv7
2026-09-112608.27875HyQuant: Hybrid-Precision Quantization for LLM AttentionJiatong Ding et al.arXiv6
2026-09-032609.02783EarlyEval: Cheaper Agent Evaluation via Early Outcome PredictionYuling Shi et al.arXiv54
2026-09-012608.29098SafeAtlas-VL: Beyond Binary Multimodal Safety with Large-Scale Data and Guard ModelsZongrui Wang et al.arXiv8
2026-09-012608.28695Weaving Visual Narratives: Agentic Image Bundle Composition Beyond Atomic Visual MatchingRong Shan et al.arXiv6
2026-08-282608.27456UrbanGround: From Local Perception to Spatial Agency in a Real-Scale CityTianjie Ju et al.arXiv54
2026-08-242608.16425ParaTempo: Efficient Parallel Reasoning via Temporal ConfidenceXuteng Zhang et al.arXiv41
2026-08-212608.19854Repo0: Design-Driven Zero-to-All Code GenerationSilin Chen et al.arXiv17
2026-08-202608.18852SkillGate: Training In-Policy Skill Selection in Long-Horizon AgentsQingyao Li et al.arXiv9
2026-08-192608.18933SkillForge: Self-Distilling Agents for Project-Specific Issue ResolutionSilin Chen et al.arXiv14
2026-08-182608.16765TRACE-Bench: Decomposing and Diagnosing Multi-Reference Image GenerationHaoran Wang et al.arXiv13
2026-08-142608.13049H2R-Bench: Benchmarking Human-to-Robot Manipulation Video Generation in World ModelsDingyi Rong et al.arXiv14
2026-08-062608.05102ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit AssignmentYijun Lu et al.arXiv35
2026-07-152607.11111Know Before Fix: QA-Driven Repository Knowledge Acquisition for Software Issue ResolutionHaotian Lin et al.arXiv13
2026-07-102607.08758Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea GenerationYifan Zhou et al.arXiv37
2026-06-252606.24775Are We Ready For An Agent-Native Memory System?Wei Zhou et al.arXiv99
2026-06-192606.19531ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?Yuyang Zhang et al.arXiv25
2026-06-182606.14024ViT-Up: Faithful Feature Upsampling for Vision TransformersKrispin Wandel et al.arXiv9
2026-06-152606.14061LLM Agents Can See Code RepositoriesDongjian Ma et al.arXiv20
2026-06-122606.08103Revisiting Articulated Parts Perception in Robot ManipulationXiaoqian Wu et al.arXiv3
2026-06-112606.11683Reason, Then Re-reason: Cross-view Revisiting Improves Spatial ReasoningChaofan Ma et al.arXiv26
2026-06-092606.07297SWE-Explore: Benchmarking How Coding Agents Explore RepositoriesShaoqiu Zhang et al.arXiv121
2026-06-092606.09811AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context RoutingJisong Cai et al.arXiv15
2026-06-092606.09348PBSD: Privileged Bayesian Self-Distillation for Long-Horizon Credit AssignmentYang Tian et al.arXiv
2026-06-022605.29707Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative DecodingJianuo Huang et al.arXiv62
2026-05-282605.26574GradSentry: Gradient Spectral Entropy for Backdoor Sample Filtering in Large Language Model Fine-TuningHaodong Zhao et al.arXiv9
2026-05-282605.28158OR-Space: A Full-Lifecycle Workspace Benchmark for Industrial Optimization AgentsChenyu Zhou et al.arXiv4
2026-05-262605.25971Anticipate and Learn: Unleashing Idle-Time Compute in Proactive AgentsHaoyi Hu et al.arXiv14
2026-05-202605.18714Semantic Generative Tuning for Unified Multimodal ModelsSongsong Yu et al.arXiv8
2026-05-142605.14306Towards Self-Evolving Agentic Literature RetrievalYuwen Du et al.arXiv4
2026-05-062605.03042ARIS: Autonomous Research via Adversarial Multi-Agent CollaborationRuofeng Yang et al.arXiv154