Avi Basa

avahal's activity

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

commented 20 papers about 10 hours ago

GTR-Turbo: Merged Checkpoint is Secretly a Free Teacher for Agentic VLM Training

Paper • 2512.13043 • Published 12 days ago • 3 •

2

VA-$π$: Variational Policy Alignment for Pixel-Aware Autoregressive Generation

Paper • 2512.19680 • Published 5 days ago • 4 •

2

How Much 3D Do Video Foundation Models Encode?

Paper • 2512.19949 • Published 4 days ago • 5 •

2

Schoenfeld's Anatomy of Mathematical Reasoning by Language Models

Paper • 2512.19995 • Published 4 days ago • 9 •

3

Spatia: Video Generation with Updatable Spatial Memory

Paper • 2512.15716 • Published 10 days ago • 16 •

2

Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning

Paper • 2512.20605 • Published 4 days ago • 31 •

2

Latent Implicit Visual Reasoning

Paper • 2512.21218 • Published 3 days ago • 38 •

2

Learning to Refocus with Video Diffusion Models

Paper • 2512.19823 • Published 5 days ago •

2

Toxicity Ahead: Forecasting Conversational Derailment on GitHub

Paper • 2512.15031 • Published 10 days ago • 1 •

2

Multi-LLM Thematic Analysis with Dual Reliability Metrics: Combining Cohen's Kappa and Semantic Similarity for Qualitative Research Validation

Paper • 2512.20352 • Published 4 days ago • 2 •

2

Simulstream: Open-Source Toolkit for Evaluation and Demonstration of Streaming Speech-to-Text Translation Systems

Paper • 2512.17648 • Published 8 days ago • 3 •

2

Memory-T1: Reinforcement Learning for Temporal Reasoning in Multi-session Agents

Paper • 2512.20092 • Published 4 days ago • 4 •

2

FaithLens: Detecting and Explaining Faithfulness Hallucination

Paper • 2512.20182 • Published 4 days ago • 7 •

2

Scaling Laws for Code: Every Programming Language Matters

Paper • 2512.13472 • Published 12 days ago • 8 •

2

Active Intelligence in Video Avatars via Closed-loop World Modeling

Paper • 2512.20615 • Published 4 days ago • 8 •

2

QuantiPhy: A Quantitative Benchmark Evaluating Physical Reasoning Abilities of Vision-Language Models

Paper • 2512.19526 • Published 5 days ago • 10 •

2

INTELLECT-3: Technical Report

Paper • 2512.16144 • Published 9 days ago • 13 •

2

C2LLM Technical Report: A New Frontier in Code Retrieval via Adaptive Cross-Attention Pooling

Paper • 2512.21332 • Published 3 days ago • 13 •

2

SAM Audio: Segment Anything in Audio

Paper • 2512.18099 • Published 7 days ago • 15 •

1

Reinforcement Learning for Self-Improving Agent with Skill Library

Paper • 2512.17102 • Published 8 days ago • 22 •

3