SWE-MISBEHAVIOR: Benchmarking and Mitigating Boundary Violations in Software Coding Agents
Paper • 2610.18206 • Published • 10
Liping Liu
JesusWhereImI
AI & ML interests
None yet
Recent Activity
upvoted a paper about 20 hours ago
SWE-MISBEHAVIOR: Benchmarking and Mitigating Boundary Violations in Software Coding Agents upvoted a paper about 20 hours ago
HexaBee-4B: Six-Language Translation with Multilingual Answering and Bidirectional Supervision upvoted a paper about 20 hours ago
What Really Works for Universal Multimodal Embeddings? A Controlled Study of Contrastive Training StrategiesOrganizations
None yet
upvoted 12
papers about 20 hours ago
HexaBee-4B: Six-Language Translation with Multilingual Answering and Bidirectional Supervision
Paper • 2610.16361 • Published • 8
What Really Works for Universal Multimodal Embeddings? A Controlled Study of Contrastive Training Strategies
Paper • 2610.15035 • Published • 10
UniForge3D: Joint 3D Reconstruction and Generation in a Shared Anchor-Guided Space
Paper • 2610.15357 • Published • 9
CineRecon: Benchmarking Frontier Models for Agentic Cinematic Reconstruction
Paper • 2610.16577 • Published • 21
GeoFix: Geometry Fixing for 4D Consistent Generation
Paper • 2610.14293 • Published • 18
VEDJE: Video-Efficient Discriminative Joint Encoder for Scalable Video-Text Retrieval
Paper • 2610.11850 • Published • 37
FlashVSR+: Efficient Video Super-Resolution via Hybrid Attention and Reward-Yield Distribution Matching
Paper • 2610.17552 • Published • 34
Self-Distillation with Verbal Regularization
Paper • 2610.16354 • Published • 29
WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution
Paper • 2610.18067 • Published • 76
SALD: Self-Referenced Advantage Learning for Diffusion Models
Paper • 2610.01496 • Published • 54
Jeva: System One Models from First Principles
Paper • 2610.18773 • Published • 272