liandun110

liandun110's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 20 papers about 3 hours ago

DynaFlow: Learning Free-Form Multi-Agent Orchestration

Paper • 2610.34467 • Published 4 days ago • 205

Representation Redistribution in Sparse Autoencoders

Paper • 2610.21240 • Published 14 days ago • 59

AV-FABLE: Audio-Visual Manipulation Forensics in Long-Form Videos

Paper • 2610.33413 • Published 5 days ago • 49

S3AC: Stabilized, Selective, and Scalable Actor-Critic for LLM Reasoning

Paper • 2610.35518 • Published 3 days ago • 33

Evolving to Match Capabilities: Improving Harness Self-Evolution via Skill Adaptation

Paper • 2610.33024 • Published 19 days ago • 31

More Memory, Better Videos? A Controlled Study of Visual Memory in Long-Video Generation

Paper • 2610.35001 • Published 3 days ago • 24

Mycelium: A Meta-Study of Hallucination Detection Across Provenance, Typology, and Granularities

Paper • 2610.33608 • Published 5 days ago • 26

RoboHarness: A Simple Harness Outperforms VLA and World Action Models

Paper • 2610.14018 • Published 13 days ago • 21

CausalAlign: Causal Alignment of Video Generation Models for Consistent Ego-Motion

Paper • 2610.29915 • Published 8 days ago • 20

EmbodiedLab: Benchmarking Embodied Agents That Act to Know

Paper • 2610.35385 • Published 3 days ago • 21

iPrefBench: A User-Centric Benchmark for Personalized Mobile Use Agents

Paper • 2610.34735 • Published 3 days ago • 21

How Far Can Coding Agents Go in Visual Generation?

Paper • 2610.19025 • Published 16 days ago • 19

Thinking-in-Bets at Test Time Reduces Sycophantic Revisions in LLM Agents

Paper • 2610.34654 • Published 3 days ago • 18

ReGE: Stronger Agents through Experience Synthesis

Paper • 2610.33861 • Published 5 days ago • 15

Rethinking Video Storage for AI Training: Breaking Cross-Frame Dependencies for Efficient Random Access

Paper • 2610.33079 • Published 8 days ago • 17

ParetoRSI-Gym: Can AI Agents Improve Language Models Across Multiple Domains?

Paper • 2610.34386 • Published 4 days ago • 15

Nested Sparsity for Scalable Pretraining and Continual Learning

Paper • 2610.31818 • Published 7 days ago • 14

Beyond Benchmarks: Can Small Open-Weight Models Get Real Coding Work Done?

Paper • 2610.34241 • Published 4 days ago • 12

RoboJev: An Open Vision-Language Judge for Robot Success Detection

Paper • 2610.33718 • Published 5 days ago • 13

DialFork: Going Beyond Factuality to Evaluate Procedural Hallucination in Conversational Agents

Paper • 2610.21561 • Published 14 days ago • 12