Avi

avahal's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

commented 6 papers about 11 hours ago

ClawBench: Can AI Agents Complete Everyday Online Tasks?

Paper • 2604.08523 • Published 2 days ago • 78 •

3

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability

Paper • 2604.06628 • Published 3 days ago • 152 •

3

HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents

Paper • 2604.07430 • Published 3 days ago • 126 •

3

MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping

Paper • 2604.08364 • Published 2 days ago • 79 •

7

When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models

Paper • 2604.08546 • Published 2 days ago • 104 •

2

SkillClaw: Let Skills Evolve Collectively with Agentic Evolver

Paper • 2604.08377 • Published 2 days ago • 143 •

5

commented 6 papers 1 day ago

INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling

Paper • 2604.07209 • Published 3 days ago • 25 •

2

SEVerA: Verified Synthesis of Self-Evolving Agents

Paper • 2603.25111 • Published 16 days ago • 24 •

3

Combee: Scaling Prompt Learning for Self-Improving Language Model Agents

Paper • 2604.04247 • Published 6 days ago • 24 •

3

MARS: Enabling Autoregressive Models Multi-Token Generation

Paper • 2604.07023 • Published 3 days ago • 28 •

3

RAGEN-2: Reasoning Collapse in Agentic RL

Paper • 2604.06268 • Published 4 days ago • 49 •

4

Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning

Paper • 2604.04746 • Published 3 days ago • 57 •

3

commented 6 papers 2 days ago

Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision

Paper • 2604.04934 • Published 5 days ago • 35 •

5

Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoning

Paper • 2604.05404 • Published 4 days ago • 38 •

4

ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation

Paper • 2604.03922 • Published 6 days ago • 49 •

4

Learning to Retrieve from Agent Trajectories

Paper • 2604.04949 • Published 12 days ago • 63 •

8

Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents

Paper • 2604.06132 • Published 4 days ago • 107 •

5

Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding

Paper • 2604.05015 • Published 5 days ago • 222 •

8

commented 2 papers 3 days ago

SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing

Paper • 2604.04911 • Published 5 days ago • 32 •

3

AURA: Always-On Understanding and Real-Time Assistance via Video Streams

Paper • 2604.04184 • Published 6 days ago • 43 •

3