SuperCorrect: Supervising and Correcting Language Models with Error-Driven Insights
Paper
β’
2410.09008
β’
Published
β’
17
papers
-
-
answerdotai/ModernBERT-base
Fill-Mask β’ Updated β’ 752k β’ β’ 868 -
answerdotai/ModernBERT-large
Fill-Mask β’ Updated β’ 85k β’ β’ 403 -
microsoft/phi-4
Text Generation β’ Updated β’ 729k β’ β’ 2.08k -
deepseek-ai/DeepSeek-R1
Text Generation β’ Updated β’ 635k β’ β’ 12.4k -
deepseek-ai/DeepSeek-R1-Zero
Text Generation β’ Updated β’ 3.67k β’ 921 -
Qwen/QwQ-32B-Preview
Text Generation β’ Updated β’ 34.2k β’ β’ 1.74k -
microsoft/Phi-3.5-MoE-instruct
Text Generation β’ Updated β’ 35.2k β’ 558 -
ibm-granite/granite-3.2-8b-instruct-preview
Text Generation β’ Updated β’ 1.62k β’ 69 -
LDJnr/Capybara
Viewer β’ Updated β’ 16k β’ 273 β’ 238 -
agentica-org/DeepScaleR-1.5B-Preview
Text Generation β’ Updated β’ 128k β’ 559 -
87
Open FinLLM Leaderboard
π₯Browse and submit large language model evaluations
-
onnx-community/Kokoro-82M-ONNX
Text-to-Speech β’ Updated β’ 15.7k β’ 144 -
HuggingFaceTB/SmolVLM2-256M-Video-Instruct
Image-Text-to-Text β’ Updated β’ 27.8k β’ 64 -
Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning
Paper β’ 2502.14768 β’ Published β’ 48 -
Menlo/AlphaMaze-v0.2-1.5B
Text Generation β’ Updated β’ 9.48k β’ 92 -
qihoo360/TinyR1-32B-Preview
Text Generation β’ Updated β’ 5.2k β’ β’ 328 -
Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment
Paper β’ 2502.16894 β’ Published β’ 31 -
microsoft/Phi-4-multimodal-instruct
Automatic Speech Recognition β’ Updated β’ 563k β’ 1.43k -
microsoft/Magma-8B
Image-Text-to-Text β’ Updated β’ 6.87k β’ 398 -
Physics of Language Models: Part 1, Context-Free Grammar
Paper β’ 2305.13673 β’ Published β’ 7 -
LoRA: Low-Rank Adaptation of Large Language Models
Paper β’ 2106.09685 β’ Published β’ 40 -
Physics of Language Models: Part 2.2, How to Learn From Mistakes on Grade-School Math Problems
Paper β’ 2408.16293 β’ Published β’ 27 -
Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process
Paper β’ 2407.20311 β’ Published β’ 5 -
Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws
Paper β’ 2404.05405 β’ Published β’ 10 -
Reverse Training to Nurse the Reversal Curse
Paper β’ 2403.13799 β’ Published β’ 13 -
Physics of Language Models: Part 3.2, Knowledge Manipulation
Paper β’ 2309.14402 β’ Published β’ 7 -
Physics of Language Models: Part 3.1, Knowledge Storage and Extraction
Paper β’ 2309.14316 β’ Published β’ 8 -
yale-nlp/FOLIO
Viewer β’ Updated β’ 1.2k β’ 613 β’ 45 -
Qwen/QwQ-32B
Text Generation β’ Updated β’ 314k β’ β’ 2.78k -
DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks
Paper β’ 2502.17157 β’ Published β’ 53 -
secemp9/TraceBack-12b
Text Generation β’ Updated β’ 60 β’ 30 -
saytes/SoT_DistilBERT
Text Classification β’ Updated β’ 839 β’ 5 -
Symbolic Mixture-of-Experts: Adaptive Skill-based Routing for Heterogeneous Reasoning
Paper β’ 2503.05641 β’ Published β’ 2 -
ds4sd/SmolDocling-256M-preview
Image-Text-to-Text β’ Updated β’ 235k β’ 1.44k -
242
SmolDocling
π¦Generate document text from images using prompts
-
SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion
Paper β’ 2503.11576 β’ Published β’ 108 -
260
WeShopAI Virtual Try On
πTransform flat-lay shots into on-model photos
-
manycore-research/SpatialLM-Llama-1B
Text Generation β’ Updated β’ 3.35k β’ 967 -
manycore-research/SpatialLM-Testset
Viewer β’ Updated β’ 107 β’ 1.52k β’ 57 -
Fin-R1: A Large Language Model for Financial Reasoning through Reinforcement Learning
Paper β’ 2503.16252 β’ Published β’ 27 -
Charting and Navigating Hugging Face's Model Atlas
Paper β’ 2503.10633 β’ Published β’ 86 -
Qwen/Qwen2.5-VL-32B-Instruct
Image-Text-to-Text β’ Updated β’ 480k β’ β’ 392 -
Expert Race: A Flexible Routing Strategy for Scaling Diffusion Transformer with Mixture of Experts
Paper β’ 2503.16057 β’ Published β’ 14 -
Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model
Paper β’ 2503.24290 β’ Published β’ 62 -
reducto/RolmOCR
Image-Text-to-Text β’ Updated β’ 123k β’ 433 -
LGAI-EXAONE/EXAONE-Deep-32B
Text Generation β’ Updated β’ 45.9k β’ 292 -
OuteAI/Llama-OuteTTS-1.0-1B-GGUF
Text-to-Speech β’ Updated β’ 10.1k β’ 61 -
microsoft/distilled_decoding
Updated β’ 2 -
lightonai/Reason-ModernColBERT
Sentence Similarity β’ Updated β’ 4.07k β’ 185