Lingshu-Cell: A generative cellular world model for transcriptome modeling toward virtual cells
Paper • 2603.25240 • Published • 71 •
3
Avi
avahal
AI & ML interests
LLMs
Recent Activity
commentedon a paper about 7 hours ago
Lingshu-Cell: A generative cellular world model for transcriptome modeling toward virtual cells commentedon a paper about 7 hours ago
CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence commentedon a paper about 7 hours ago
LongCat-Next: Lexicalizing Modalities as Discrete TokensOrganizations
None yet
commented 4
papers about 7 hours ago
CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence
Paper • 2603.28032 • Published • 200 •
2
LongCat-Next: Lexicalizing Modalities as Discrete Tokens
Paper • 2603.27538 • Published • 116 •
3
FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization
Paper • 2603.19835 • Published • 286 •
4
commented 7
papers about 17 hours ago
Gen-Searcher: Reinforcing Agentic Search for Image Generation
Paper • 2603.28767 • Published • 50 •
3
Towards a Medical AI Scientist
Paper • 2603.28589 • Published • 80 •
3
TAPS: Task Aware Proposal Distributions for Speculative Sampling
Paper • 2603.27027 • Published • 132 •
4
Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
Paper • 2603.25158 • Published • 43 •
14
PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference
Paper • 2603.25730 • Published • 45 •
3
ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling
Paper • 2603.25746 • Published • 149 •
6
Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models
Paper • 2603.25716 • Published • 145 •
4
commented 4
papers 6 days ago
Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Paper • 2603.24472 • Published • 46 •
7
UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience
Paper • 2603.24533 • Published • 44 •
4
T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search
Paper • 2603.22341 • Published • 36 •
3
EVA: Efficient Reinforcement Learning for End-to-End Video Agent
Paper • 2603.22918 • Published • 42 •
5
commented 5
papers 7 days ago
PEARL: Personalized Streaming Video Understanding Model
Paper • 2603.20422 • Published • 40 •
4
SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning
Paper • 2603.23483 • Published • 59 •
4
WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG
Paper • 2603.23497 • Published • 90 •
4
MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding
Paper • 2603.22458 • Published • 131 •
6
LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning
Paper • 2603.21065 • Published • 77 •
4