From Production Traffic to Post-Training: Building a Self-Hosted LLM That Covers the Corporate Request Mix Paper • 2609.01572 • Published 7 days ago • 33
SIGNPOST-Bench: Benchmarking Text-Vision Conflict Resolution in Multimodal Large Language Models Paper • 2608.04244 • Published Aug 4 • 3
LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, and Frame Interpolation with Video Diffusion Models Paper • 2607.08770 • Published Jul 9 • 37
Multi-Turn Agentic Scientific Literature Search via Workflow Induction Paper • 2607.00597 • Published Jul 1 • 31
Track2View: 4D-Consistent Camera-Controlled Video Generation via Paired 3D Point Tracks Paper • 2606.15534 • Published Jun 14 • 13
AsyncTool: Evaluating the Asynchronous Function Calling Capability under Multi-Task Scenarios Paper • 2605.27995 • Published May 27 • 17