Beyond Simply Environment Scaling: Designing Effective Environment Distributions for Multimodal Agent Learning
Paper • 2608.03571 • Published • 40
Kevin Li
kaiweili
AI & ML interests
None yet
Recent Activity
upvoted a paper about 18 hours ago
Beyond Simply Environment Scaling: Designing Effective Environment Distributions for Multimodal Agent Learning upvoted a paper about 18 hours ago
Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains upvoted a paper 7 days ago
LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World TasksOrganizations
None yet
upvoted 2
papers about 18 hours ago
upvoted 4
papers 7 days ago
LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks
Paper • 2608.01964 • Published • 166
Progressive Agent Skill Generation via Reinforcement Learning
Paper • 2608.01678 • Published • 58
SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks
Paper • 2608.02023 • Published • 155
UEmbed: Unified Sparse and Dense Multimodal Embeddings
Paper • 2608.02583 • Published • 50
upvoted 7
papers about 2 months ago
V-Zero: Answer-Label-Free On-Policy Distillation with Contrastive Evidence Gating for Fine-Grained Visual Reasoning
Paper • 2606.25319 • Published • 27
MVTrack4Gen: Multi-View Point Tracking as Geometric Supervision for 4D Video Generation
Paper • 2606.26087 • Published • 35
GUI vs. CLI: Execution Bottlenecks in Screen-Only and Skill-Mediated Computer-Use Agents
Paper • 2606.24551 • Published • 28
Getting Better at Working With You: Compiling User Corrections into Runtime Enforcement for Coding Agents
Paper • 2606.13174 • Published • 5
EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments
Paper • 2606.13681 • Published • 143
VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding
Paper • 2606.05259 • Published • 39
EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery
Paper • 2606.13662 • Published • 31