70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float Paper • 2504.11651 • Published 10 days ago • 18
Unsloth Dynamic 2.0 Quants Collection New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & outperforms all leading quantization methods. • 9 items • Updated about 20 hours ago • 31
OpenMathReasoning Collection Models and datasets from "AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset" • 7 items • Updated 1 day ago • 23
An LMM for Efficient Video Understanding via Reinforced Compression of Video Cubes Paper • 2504.15270 • Published 5 days ago • 10
Describe Anything Collection Multimodal Large Language Models for Detailed Localized Image and Video Captioning • 7 items • Updated 1 day ago • 40
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model? Paper • 2504.13837 • Published 8 days ago • 98
Pushing the Limits of Large Language Model Quantization via the Linearity Theorem Paper • 2411.17525 • Published Nov 26, 2024 • 4
ReTool: Reinforcement Learning for Strategic Tool Use in LLMs Paper • 2504.11536 • Published 11 days ago • 58
xVerify: Efficient Answer Verifier for Reasoning Model Evaluations Paper • 2504.10481 • Published 12 days ago • 84
RealHarm: A Collection of Real-World Language Model Application Failures Paper • 2504.10277 • Published 12 days ago • 11
PRIMA.CPP: Speeding Up 70B-Scale LLM Inference on Low-Resource Everyday Home Clusters Paper • 2504.08791 • Published 19 days ago • 123
Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model Paper • 2504.08685 • Published 15 days ago • 121
FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis Paper • 2504.04842 • Published 19 days ago • 34
OmniSVG: A Unified Scalable Vector Graphics Generation Model Paper • 2504.06263 • Published 18 days ago • 151