tuanzi
e-tuanzi
AI & ML interests
None yet
Recent Activity
updated
a collection
5 days ago
video
updated
a collection
5 days ago
agent
updated
a collection
5 days ago
video
Organizations
None yet
agent
-
Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem
Paper • 2512.24873 • Published • 96 -
AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents
Paper • 2512.23343 • Published • 25 -
BEDA: Belief Estimation as Probabilistic Constraints for Performing Strategic Dialogue Acts
Paper • 2512.24885 • Published • 4 -
An Information Theoretic Perspective on Agentic System Design
Paper • 2512.21720 • Published • 7
video
-
Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation
Paper • 2512.24271 • Published • 50 -
FlowBlending: Stage-Aware Multi-Model Sampling for Fast and High-Fidelity Video Generation
Paper • 2512.24724 • Published • 6 -
Pretraining Frame Preservation in Autoregressive Video Memory Compression
Paper • 2512.23851 • Published • 22 -
PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation
Paper • 2512.24551 • Published • 18
3d
light
-
Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models
Paper • 2512.24618 • Published • 129 -
LiveTalk: Real-Time Multimodal Interactive Video Diffusion via Improved On-Policy Distillation
Paper • 2512.23576 • Published • 64 -
Yume-1.5: A Text-Controlled Interactive World Generation Model
Paper • 2512.22096 • Published • 58 -
Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion
Paper • 2512.23709 • Published • 48
game
multimodal
3d
agent
-
Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem
Paper • 2512.24873 • Published • 96 -
AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents
Paper • 2512.23343 • Published • 25 -
BEDA: Belief Estimation as Probabilistic Constraints for Performing Strategic Dialogue Acts
Paper • 2512.24885 • Published • 4 -
An Information Theoretic Perspective on Agentic System Design
Paper • 2512.21720 • Published • 7
light
-
Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models
Paper • 2512.24618 • Published • 129 -
LiveTalk: Real-Time Multimodal Interactive Video Diffusion via Improved On-Policy Distillation
Paper • 2512.23576 • Published • 64 -
Yume-1.5: A Text-Controlled Interactive World Generation Model
Paper • 2512.22096 • Published • 58 -
Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion
Paper • 2512.23709 • Published • 48
video
-
Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation
Paper • 2512.24271 • Published • 50 -
FlowBlending: Stage-Aware Multi-Model Sampling for Fast and High-Fidelity Video Generation
Paper • 2512.24724 • Published • 6 -
Pretraining Frame Preservation in Autoregressive Video Memory Compression
Paper • 2512.23851 • Published • 22 -
PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation
Paper • 2512.24551 • Published • 18
game