Turns Matter: Advancing Streaming Video RL via Turn-Level Credit
Paper • 2611.06728 • Published • 92
AI & ML interests
NextTransformer: The comprehensive, cutting-edge open-source framework, benchmark and auto-research platform for next-generation Transformers
Recent Activity
View all activity
XiangnanW
submitted a
paper to Daily Papers about 9 hours ago
xjxyys
submitted a
paper to Daily Papers 8 days ago
XiangnanW
authored 9
papers 9 days ago
Scaling in Games: Continued Pre-Training For Embodied Agents In Diverse Virtual Worlds
Paper • 2610.28698 • Published • 73
Can World and Action Modeling Benefit Each Other under Unified Causal Training?
Paper • 2610.21095 • Published • 29
Video-Arena: A Scalable Agentic Video Benchmark for Spatiotemporal Capability
Paper • 2610.14158 • Published • 12
Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse
Paper • 2605.09965 • Published • 1
UAOR: Uncertainty-aware Observation Reinjection for Vision-Language-Action Models
Paper • 2602.18020 • Published
SKIP: Sparse Keyframe Interpolation Paradigm for Efficient Embodied World Models
Paper • 2606.00664 • Published • 1
BridgeV2W: Bridging Video Generation Models to Embodied World Models via Embodiment Masks
Paper • 2602.03793 • Published
Multi-View Video Diffusion Policy: A 3D Spatio-Temporal-Aware Video Action Model
Paper • 2604.03181 • Published
BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models
Paper • 2506.07961 • Published • 12
xjxyys
authored 2
papers 15 days ago
selensu
submitted a
paper to Daily Papers 20 days ago
selensu
authored a
paper 20 days ago
X-Zhang
authored 4
papers 3 months ago
Mitigating Error Accumulation in Co-Speech Motion Generation via Global Rotation Diffusion and Multi-Level Constraints
Paper • 2511.10076 • Published
EchoMask: Speech-Queried Attention-based Mask Modeling for Holistic Co-Speech Motion Generation
Paper • 2504.09209 • Published
StreamTalk: Streaming Co-Speech Gesture Generation with Key-Pose Anchoring
Paper • 2608.01643 • Published
SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis
Paper • 2412.16563 • Published
yitianlian
authored a
paper 9 months ago