Avi

avahal's activity

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

commented 4 papers about 9 hours ago

Video-Based Reward Modeling for Computer-Use Agents

Paper • 2603.10178 • Published 6 days ago • 36 •

3

IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse

Paper • 2603.12201 • Published 4 days ago • 45 •

4

Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections

Paper • 2603.12180 • Published 4 days ago • 56 •

3

Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training

Paper • 2603.12255 • Published 4 days ago • 78 •

3

commented 4 papers about 10 hours ago

Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion

Paper • 2603.06577 • Published 10 days ago • 43 •

5

MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data

Paper • 2603.09206 • Published 6 days ago • 45 •

3

Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs

Paper • 2603.09906 • Published 6 days ago • 62 •

3

Geometry-Guided Reinforcement Learning for Multi-view Consistent 3D Scene Editing

Paper • 2603.03143 • Published 13 days ago • 137 •

8

commented 4 papers about 11 hours ago

LLM2Vec-Gen: Generative Embeddings from Large Language Models

Paper • 2603.10913 • Published 5 days ago • 34 •

3

Flash-KMeans: Fast and Memory-Efficient Exact K-Means

Paper • 2603.09229 • Published 6 days ago • 68 •

3

OpenClaw-RL: Train Any Agent Simply by Talking

Paper • 2603.10165 • Published 6 days ago • 101 •

5

Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning

Paper • 2603.04597 • Published 12 days ago • 159 •

3

commented 2 papers 6 days ago

Believe Your Model: Distribution-Guided Confidence Calibration

Paper • 2603.03872 • Published 12 days ago • 38 •

3

Lost in Stories: Consistency Bugs in Long Story Generation by LLMs

Paper • 2603.05890 • Published 10 days ago • 83 •

4

commented 5 papers 7 days ago

WildActor: Unconstrained Identity-Preserving Video Generation

Paper • 2603.00586 • Published 16 days ago • 34 •

5

Progressive Residual Warmup for Language Model Pretraining

Paper • 2603.05369 • Published 11 days ago • 33 •

5

Planning in 8 Tokens: A Compact Discrete Tokenizer for Latent World Model

Paper • 2603.05438 • Published 11 days ago • 36 •

4

BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning

Paper • 2603.04918 • Published 11 days ago • 54 •

7

Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders

Paper • 2603.06569 • Published 10 days ago • 105 •

4

commented a paper 10 days ago

RoboPocket: Improve Robot Policies Instantly with Your Phone

Paper • 2603.05504 • Published 11 days ago • 31 •

4