SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks
Paper • 2604.08865 • Published • 26 •
3
Avi
avahal
AI & ML interests
LLMs
Recent Activity
commentedon a paper about 2 hours ago
SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks commentedon a paper about 2 hours ago
ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents commentedon a paper 2 days ago
Uni-ViGU: Towards Unified Video Generation and Understanding via A Diffusion-Based Video GeneratorOrganizations
None yet
commented 2
papers about 2 hours ago
commented 3
papers 2 days ago
Uni-ViGU: Towards Unified Video Generation and Understanding via A Diffusion-Based Video Generator
Paper • 2604.08121 • Published • 41 •
4
Strips as Tokens: Artist Mesh Generation with Native UV Segmentation
Paper • 2604.09132 • Published • 48 •
3
QuanBench+: A Unified Multi-Framework Benchmark for LLM-Based Quantum Code Generation
Paper • 2604.08570 • Published • 120 •
5
commented 6
papers 3 days ago
ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion
Paper • 2604.09450 • Published • 18 •
4
Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory
Paper • 2604.08995 • Published • 43 •
2
EXAONE 4.5 Technical Report
Paper • 2604.08644 • Published • 58 •
3
RefineAnything: Multimodal Region-Specific Refinement for Perfect Local Details
Paper • 2604.06870 • Published • 39 •
5
FORGE:Fine-grained Multimodal Evaluation for Manufacturing Scenarios
Paper • 2604.07413 • Published • 90 •
5
WildDet3D: Scaling Promptable 3D Detection in the Wild
Paper • 2604.08626 • Published • 231 •
4
commented 9
papers 6 days ago
ClawBench: Can AI Agents Complete Everyday Online Tasks?
Paper • 2604.08523 • Published • 255 •
5
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
Paper • 2604.06628 • Published • 310 •
7
HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents
Paper • 2604.07430 • Published • 178 •
4
MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping
Paper • 2604.08364 • Published • 95 •
9
When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models
Paper • 2604.08546 • Published • 113 •
4
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
Paper • 2604.08377 • Published • 276 •
6
INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling
Paper • 2604.07209 • Published • 35 •
2
SEVerA: Verified Synthesis of Self-Evolving Agents
Paper • 2603.25111 • Published • 31 •
3
Combee: Scaling Prompt Learning for Self-Improving Language Model Agents
Paper • 2604.04247 • Published • 30 •
3