Constantin

Alexandre-Numind's activity

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

upvoted a paper about 10 hours ago

Improving Test-Time Scaling with Adaptive Looped Transformers

Paper • 2609.35748 • Published 4 days ago • 54

upvoted a paper about 12 hours ago

Post-Training Leaves Behavioral Shadows on Unrelated Decisions

Paper • 2609.29233 • Published 8 days ago • 271

upvoted a paper 24 days ago

EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction

Paper • 2609.02783 • Published about 1 month ago • 62

upvoted 2 papers about 2 months ago

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs

Paper • 2608.03573 • Published Aug 6 • 61

On-Policy Self-Distillation without Any Supervision

Paper • 2608.06296 • Published Aug 9 • 181

upvoted a paper 2 months ago

Beacon: Knowing When and How to Perform Agentic Visual Reasoning

Paper • 2607.28595 • Published Jul 30 • 56

upvoted a paper 3 months ago

DOPD: Dual On-policy Distillation

Paper • 2606.30626 • Published Jun 29 • 115

upvoted a collection 5 months ago

NuExtract3

Collection

12 items • Updated May 26 • 17

upvoted a paper 6 months ago

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

Paper • 2604.06628 • Published Apr 8 • 130

upvoted a paper 7 months ago

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

Paper • 2603.04597 • Published Mar 4 • 39

upvoted an article 7 months ago

view article

Article

From GRPO to DAPO and GSPO: What, Why, and How

• 

NormalUhr

•

Aug 9, 2025

• 145

upvoted 2 papers 8 months ago

Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text

Paper • 2601.22975 • Published Jan 30 • 113

Kimi K2.5: Visual Agentic Intelligence

Paper • 2602.02276 • Published Feb 2 • 278

upvoted a paper 9 months ago

Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization

Paper • 2601.05432 • Published Jan 8 • 170

upvoted a paper 10 months ago

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Paper • 2512.02556 • Published Dec 2, 2025 • 274

upvoted a paper about 1 year ago

Thyme: Think Beyond Images

Paper • 2508.11630 • Published Aug 15, 2025 • 81

upvoted a collection over 1 year ago

NuExtract-2.0

Collection

Models specialized in extracting structured information (JSON) from text, PDFs, scans, spreadsheets, etc. • 9 items • Updated Mar 2 • 31

upvoted 3 papers almost 2 years ago

Evaluating Language Models as Synthetic Data Generators

Paper • 2412.03679 • Published Dec 4, 2024 • 47

Critical Tokens Matter: Token-Level Contrastive Estimation Enhence LLM's Reasoning Capability

Paper • 2411.19943 • Published Nov 29, 2024 • 63

OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation

Paper • 2412.02592 • Published Dec 3, 2024 • 24