Agentic Transaction: Towards ACID-Compliant Agent Systems Paper • 2608.13900 • Published 6 days ago • 25
Relevant but Incomplete: Referential Dangling as a Paradigm-Level Failure Mode in Hard Prompt Compression Paper • 2608.04569 • Published 15 days ago • 13
Uncertainty-Aware World Model for Aerial Image-Goal Navigation Paper • 2608.05597 • Published 14 days ago • 12
AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning Paper • 2608.05987 • Published 14 days ago • 95
Better, Stronger, Faster, and Broader: Structured All-Mask Prediction for MLLM-Based Segmentation Paper • 2608.02791 • Published 17 days ago • 5
Push-Wiper: Toward General-Purpose Robotic Cleaning across Varied Stains and Surfaces with Segmented Pushing Trajectories Paper • 2608.00730 • Published 19 days ago • 8
ST-WAM: Semantic-Temporal World Action Model for Robust Manipulation under Visual Distribution Shifts Paper • 2607.28993 • Published 20 days ago • 7
TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training Paper • 2607.05804 • Published Jul 7 • 20
TurboServe: Serving Streaming Video Generation Efficiently and Economically Paper • 2606.19271 • Published Jun 17 • 38
CausalMix: Data Mixture as Causal Inference for Language Model Training Paper • 2607.01104 • Published Jul 1 • 21
LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing Paper • 2606.26740 • Published Jun 25 • 82
VeriEvol: Scaling Multimodal Mathematical Reasoning via Verifiable Evol-Instruct Paper • 2606.23543 • Published Jun 22 • 6
RhymeFlow: Training-Free Acceleration for Video Generation with Asynchronous Denoising Flow Scheduling Paper • 2606.06309 • Published Jun 4 • 11
MBench: A Comprehensive Benchmark on Memory Capability for Video World Models Paper • 2606.00793 • Published Jun 8 • 11
Parametric Social Identity Injection and Diversification in Public Opinion Simulation Paper • 2603.16142 • Published Jun 1 • 1
Agent libOS: A Library-OS-Inspired Runtime for Long-Running, Capability-Controlled LLM Agents Paper • 2606.03895 • Published Jun 2 • 3
Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation Paper • 2606.02684 • Published Jun 1 • 17
Does Seeing More Mean Knowing More? Mono-Anchored Advantage Normalization for Multi-Source Visual Reasoning Paper • 2605.25437 • Published May 25 • 17
SimuWoB: Simulating Real-World Mobile Apps for Fast and Faithful GUI Agent Benchmarking Paper • 2605.25160 • Published May 24 • 9