Chmielewski

Eryk-Chmielewski's activity

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

upvoted 2 papers about 9 hours ago

Tensor Product Attention Is All You Need

Paper • 2501.06425 • Published 16 days ago • 75

Reasoning Language Models: A Blueprint

Paper • 2501.11223 • Published 8 days ago • 25

upvoted 13 papers about 10 hours ago

SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution

Paper • 2501.05040 • Published 18 days ago • 15

The GAN is dead; long live the GAN! A Modern GAN Baseline

Paper • 2501.05441 • Published 18 days ago • 85

Transformer^2: Self-adaptive LLMs

Paper • 2501.06252 • Published 19 days ago • 51

Evolving Deeper LLM Thinking

Paper • 2501.09891 • Published 11 days ago • 98

Humanity's Last Exam

Paper • 2501.14249 • Published 3 days ago • 24

Sigma: Differential Rescaling of Query, Key and Value for Efficient Language Models

Paper • 2501.13629 • Published 4 days ago • 39

SRMT: Shared Memory for Multi-agent Lifelong Pathfinding

Paper • 2501.13200 • Published 5 days ago • 54

O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning

Paper • 2501.12570 • Published 6 days ago • 20

Autonomy-of-Experts Models

Paper • 2501.13074 • Published 5 days ago • 36

Kimi k1.5: Scaling Reinforcement Learning with LLMs

Paper • 2501.12599 • Published 6 days ago • 62

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Paper • 2501.12948 • Published 5 days ago • 213

Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training

Paper • 2501.11425 • Published 7 days ago • 76

MMVU: Measuring Expert-Level Multi-Discipline Video Understanding

Paper • 2501.12380 • Published 6 days ago • 76

upvoted a collection 5 days ago

DeepSeek R1 AWQ

Collection

7 items • Updated 5 days ago • 4

upvoted 2 collections 7 days ago

Unsloth 4-bit Dynamic Quants

Collection

Unsloths Dynamic 4bit Quants selectively skips quantizing certain parameters; greatly improving accuracy while only using <10% more VRAM than BnB 4bit • 13 items • Updated 3 days ago • 23

DeepSeek R1 (All Versions)

Collection

DeepSeek R1 - the most powerful reasoning open-source model - available in GGUF, original & 4-bit formats. Includes Llama & Qwen distilled models. • 27 items • Updated about 14 hours ago • 65

upvoted 2 papers 14 days ago

Search-o1: Agentic Search-Enhanced Large Reasoning Models

Paper • 2501.05366 • Published 18 days ago • 80

CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings

Paper • 2501.01257 • Published 25 days ago • 48