Hunar Batra PRO

hunarbatra's activity

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

upvoted 7 papers 3 days ago

MCJudgeBench: A Benchmark for Constraint-Level Judge Evaluation in Multi-Constraint Instruction Following

Paper • 2605.03858 • Published May 5 • 1

Towards Understanding Multimodal Fine-Tuning: Spatial Features

Paper • 2602.08713 • Published Feb 6 • 1

EVCL: Elastic Variational Continual Learning with Weight Consolidation

Paper • 2406.15972 • Published Jun 23, 2024 • 1

Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought

Paper • 2403.05518 • Published Mar 8, 2024 • 3

Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks

Paper • 2605.01417 • Published May 2 • 2

Reasoning Fine-Tuning Induces Persistent Latent Policy States

Paper • 2607.18532 • Published 18 days ago • 1

Constitutional Midtraining: Content Presence Drives Alignment Gains

Paper • 2607.26654 • Published 9 days ago • 6

upvoted a collection 9 days ago

Constitutional Midtraining

Collection

Data and models for the paper 'Constitutional Midtraining: Content Presence Drives Alignment Gains' . • 17 items • Updated 10 days ago • 3

upvoted a collection about 2 months ago

Lie Detection

Collection

Did you lie? Evaluating Lie Detectors across Model Scale and Belief-Verified Model Organisms • 9 items • Updated Jun 10 • 6

upvoted 3 collections 7 months ago

gemma-2-9b-it-user-gender

Collection

6 items • Updated Sep 30, 2025 • 2

Llama-3.1-8B-Instruct-taboo

Collection

20 items • Updated Jan 5 • 1

Activation Oracles

Collection

12 items • Updated Dec 26, 2025 • 20

upvoted an article 7 months ago

view article

Article

NVIDIA Cosmos Reason 2 Brings Advanced Reasoning To Physical AI

• 

nvidia

•

Jan 5

• 64

upvoted a collection 7 months ago

Physical AI

Collection

Collection of open, commercial-grade datasets for physical AI developers • 57 items • Updated 4 days ago • 178

upvoted 2 papers 9 months ago

SpatialThinker: Reinforcing 3D Reasoning in Multimodal LLMs via Spatial Rewards

Paper • 2511.07403 • Published Nov 10, 2025 • 14

Measuring what Matters: Construct Validity in Large Language Model Benchmarks

Paper • 2511.04703 • Published Nov 3, 2025 • 8

upvoted an article 10 months ago

view article

Article

Smol2Operator: Post-Training GUI Agents for Computer Use

• 
• 
• +3

A-Mahla, merve, sergiopaniego, reach-vb, lewtun

•

Sep 23, 2025

• 138

upvoted a paper about 1 year ago

Group Sequence Policy Optimization

Paper • 2507.18071 • Published Jul 24, 2025 • 321

upvoted a paper over 1 year ago

Skywork R1V2: Multimodal Hybrid Reinforcement Learning for Reasoning

Paper • 2504.16656 • Published Apr 23, 2025 • 59

upvoted a collection over 1 year ago

VisionLM

Collection

1929 items • Updated May 25 • 151