ClawBench: Can AI Agents Complete Everyday Online Tasks?
Paper • 2604.08523 • Published • 243 •
5
Avi
avahal
AI & ML interests
LLMs
Recent Activity
commentedon a paper 3 days ago
ClawBench: Can AI Agents Complete Everyday Online Tasks? commentedon a paper 3 days ago
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability commentedon a paper 3 days ago
HY-Embodied-0.5: Embodied Foundation Models for Real-World AgentsOrganizations
None yet
commented 12
papers 3 days ago
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
Paper • 2604.06628 • Published • 295 •
7
HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents
Paper • 2604.07430 • Published • 154 •
4
MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping
Paper • 2604.08364 • Published • 92 •
8
When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models
Paper • 2604.08546 • Published • 109 •
4
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
Paper • 2604.08377 • Published • 260 •
6
INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling
Paper • 2604.07209 • Published • 33 •
2
SEVerA: Verified Synthesis of Self-Evolving Agents
Paper • 2603.25111 • Published • 27 •
3
Combee: Scaling Prompt Learning for Self-Improving Language Model Agents
Paper • 2604.04247 • Published • 25 •
3
MARS: Enabling Autoregressive Models Multi-Token Generation
Paper • 2604.07023 • Published • 33 •
3
RAGEN-2: Reasoning Collapse in Agentic RL
Paper • 2604.06268 • Published • 57 •
4
Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning
Paper • 2604.04746 • Published • 65 •
3
commented 8
papers 5 days ago
Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision
Paper • 2604.04934 • Published • 42 •
5
Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoning
Paper • 2604.05404 • Published • 41 •
4
ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation
Paper • 2604.03922 • Published • 52 •
4
Learning to Retrieve from Agent Trajectories
Paper • 2604.04949 • Published • 67 •
8
Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents
Paper • 2604.06132 • Published • 111 •
5
Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding
Paper • 2604.05015 • Published • 227 •
8
SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing
Paper • 2604.04911 • Published • 35 •
3
AURA: Always-On Understanding and Real-Time Assistance via Video Streams
Paper • 2604.04184 • Published • 46 •
3