CoEvoWhen: Policy-Tool Coevolution for Ultra-Long Video Temporal Grounding Paper • 2609.40048 • Published 5 days ago • 8
Scaling Properties of Same-Family On-Policy Distillation Paper • 2609.32722 • Published 9 days ago • 318
Beyond Dyadic Memory: Interaction-Aware Multimodal Memory with Adaptive Agentic Retrieval for Multi-Party Spoken Conversations Paper • 2609.32522 • Published 9 days ago • 80
IterSynth: Rethinking Deep Search Agents via Role-Decoupled Iterative Synthesis Paper • 2609.29444 • Published 11 days ago • 21
SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue Paper • 2609.26780 • Published 13 days ago • 102
RoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks? Paper • 2609.05324 • Published about 1 month ago • 28
ZipTok3D: High-Fidelity 3D Tokenization with Compact Token Prefixes Paper • 2609.01740 • Published Sep 1 • 29
LayerRecall: A State-Conditioned Memory Router for Long-Horizon Consistency in Video Generation Paper • 2608.28460 • Published Aug 28 • 29
Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion Paper • 2608.19567 • Published Aug 20 • 34
MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Use Paper • 2608.20202 • Published Aug 20 • 34
SkillEvo: Self-Renewing Evolution Gradients from Multi-Turn Interaction Feedback Paper • 2608.13120 • Published Aug 13 • 32
HiFi-BRep: High-Fidelity Latent Representation for Robust B-Rep Generation Paper • 2608.16485 • Published Aug 17 • 1
SPARGen: Unifying Spatial Perception and Reasoning through Native Multimodal Generation Paper • 2608.14138 • Published Aug 14 • 1
MobileMem: Learning from a Year of Mobile Experiences Paper • 2608.13606 • Published Aug 11 • 27
MobileMem: Learning from a Year of Mobile Experiences Paper • 2608.13606 • Published Aug 11 • 27