Lize Pirenne

Inversta's activity

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

upvoted a paper about 19 hours ago

Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation

Paper • 2604.10098 • Published 18 days ago • 77

upvoted 4 papers 5 days ago

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping

Paper • 2604.11297 • Published 16 days ago • 138

Reinforcement Learning via Value Gradient Flow

Paper • 2604.14265 • Published 14 days ago • 7

Continuous Adversarial Flow Models

Paper • 2604.11521 • Published 16 days ago • 10

From P(y|x) to P(y): Investigating Reinforcement Learning in Pre-train Space

Paper • 2604.14142 • Published 14 days ago • 29

upvoted a paper 14 days ago

FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling

Paper • 2604.06916 • Published 21 days ago • 34

upvoted 11 papers 15 days ago

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

Paper • 2604.07209 • Published 21 days ago • 36

DMax: Aggressive Parallel Decoding for dLLMs

Paper • 2604.08302 • Published 20 days ago • 51

TriAttention: Efficient Long Reasoning with Trigonometric KV Compression

Paper • 2604.04921 • Published 23 days ago • 110

GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning

Paper • 2604.02721 • Published 26 days ago • 375

Adam's Law: Textual Frequency Law on Large Language Models

Paper • 2604.02176 • Published 27 days ago • 497

FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization

Paper • 2603.19835 • Published Mar 20 • 348

DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models

Paper • 2603.26164 • Published Mar 27 • 362

LongCat-Next: Lexicalizing Modalities as Discrete Tokens

Paper • 2603.27538 • Published about 1 month ago • 145

Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale

Paper • 2603.25040 • Published Mar 26 • 131

MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding

Paper • 2603.22458 • Published Mar 23 • 135

Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazing

Paper • 2603.12254 • Published Mar 12 • 22

upvoted 3 papers 16 days ago

InCoder-32B: Code Foundation Model for Industrial Scenarios

Paper • 2603.16790 • Published Mar 17 • 308

Demystifing Video Reasoning

Paper • 2603.16870 • Published Mar 17 • 371

Lost in Backpropagation: The LM Head is a Gradient Bottleneck

Paper • 2603.10145 • Published Mar 10 • 13