On the Design of Hyper-Connections: Simplification, Stability, and Scalability Paper • 2611.05984 • Published 14 days ago • 32
From Pixels to Actions - Towards Native Vision-Language-Action Policies Paper • 2611.06918 • Published 13 days ago • 62
Wave Forcing: Towards Speed-of-Light Streaming Video Generation Paper • 2611.00859 • Published 18 days ago • 130
EnvSched: Environment-Aware Scheduling for Rollout-Efficient Agent Reinforcement Learning Paper • 2610.37609 • Published 22 days ago • 11
Work Agents: Systems, Capabilities, and Optimization Paper • 2610.35845 • Published 23 days ago • 116
Cola2: Co-Adaptive Hierarchical Language Modeling with Continuous Semantic Compression and Balanced Discrete Generation Paper • 2610.31305 • Published 27 days ago • 18
HexaShell: A Thin Harness for Exploring the Limits of VLM Agents as Robot Coding Agents Paper • 2610.23479 • Published Oct 16 • 74
Execution Before Memory: Diagnosing Memory Failures in Video World Models Paper • 2610.23542 • Published Oct 16 • 28
Can World and Action Modeling Benefit Each Other under Unified Causal Training? Paper • 2610.21095 • Published Oct 15 • 28
Rethinking World-Action Model for Compositional and In-Context Robotic Manipulation Paper • 2610.02368 • Published Oct 1 • 55
OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction Paper • 2610.01762 • Published Oct 1 • 73
EngiWorld: What Can Frontier Agents Deliver in Professional Engineering Environments? Paper • 2609.37686 • Published Sep 29 • 47
Learning Native Reflection in Unified Models with Interleaved Reinforcement Learning Paper • 2609.35767 • Published Sep 28 • 42
SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness Paper • 2609.20519 • Published Sep 17 • 90
SenseNova-U1.5: Towards Native Unified Visual Intelligence Paper • 2609.11929 • Published Sep 10 • 137
OpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining Paper • 2609.07398 • Published Sep 7 • 70
Uncovering Understanding-Generation Synergy in Native Unified Multimodal Models: From Representation, Task to System Paper • 2609.01607 • Published Sep 1 • 24
JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution Paper • 2608.25593 • Published Aug 26 • 63