SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Paper • 2608.03573 • Published 6 days ago • 46
Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains Paper • 2608.09873 • Published 2 days ago • 22
LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks Paper • 2608.01964 • Published 9 days ago • 166
UEmbed: Unified Sparse and Dense Multimodal Embeddings Paper • 2608.02583 • Published 9 days ago • 50
Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence Paper • 2606.15932 • Published Jun 16 • 38
GUI vs. CLI: Execution Bottlenecks in Screen-Only and Skill-Mediated Computer-Use Agents Paper • 2606.24551 • Published Jun 22 • 28