Rethinking Expressivity and Efficiency in Test-Time Training Paper • 2608.21308 • Published 9 days ago • 1
AgentWeave: Routing Before Reasoning for Efficient Function Calling in Tool-Rich Language Models Paper • 2608.23078 • Published 6 days ago • 1
Giga-Embeddings: Mixture-of-Experts Encoders for High-Throughput Text Embeddings Paper • 2608.23806 • Published 6 days ago • 1
Gated Activation Steering for Reducing Sycophancy & Hallucination in Medical Question Answering Paper • 2608.23666 • Published 6 days ago • 1
Tunable Tool-Call Rates in LLM Agents via Representation Steering Paper • 2608.25198 • Published 5 days ago • 1
Plans You Can Check: Verifier-Grounded Learning of an Open-Weight Planner for Executable Video-Editing Paper • 2608.25622 • Published 4 days ago • 1
RTPO: Reverse-Turn Policy Optimization for Stabilizing Agentic RL Training Paper • 2608.18682 • Published 11 days ago • 2
Semantic Overlays: Mitigating Prompt Injection with Annotations Beyond Tokens and Steering Vectors Paper • 2608.23873 • Published 6 days ago • 1
RecurSE: Bounded Recursive Self-Evaluation for LLM Rubric Judges Paper • 2608.24231 • Published 5 days ago • 1
TacForcing: Streaming Action Generation with Execution-Time Tactile Feedback Paper • 2608.25798 • Published 4 days ago • 5
Zero-WAM: In-Context World-Action Modeling from Human Videos for Open-Ended Task Generalization Paper • 2608.26103 • Published 4 days ago • 17
From Seeing to Acting: Smart Glasses as First-Person Intelligence Platforms Paper • 2608.24877 • Published 5 days ago • 10
Super Star: Towards Streaming Real-time Interactive Agents for Digital Humans Paper • 2608.24909 • Published Jul 22 • 5
MA-VLA: Multi-Arm Vision-Language-Action Model for Collaboration and Compositional Generalization Paper • 2608.25864 • Published 4 days ago • 9
Latent Action as Intention Enables Efficient Future Imagination for World Action Models Paper • 2608.24882 • Published 5 days ago • 1
Towards a Densing Law for User Representation Learning at Billion-Scale Capacity Paper • 2608.23392 • Published 6 days ago • 27
Self-OPD: On-Policy Distillation for Flow Matching Models without Teacher Paper • 2608.26872 • Published 3 days ago • 69
CritICL: Inference-Time Weak-to-Strong Generalization from Small Language Model Failure Modes Paper • 2608.27455 • Published 3 days ago • 8
StreamPI: Streaming Multimodal Temporal Modeling for Vision-Language-Action Models Paper • 2608.26067 • Published 4 days ago • 18