AI & ML interests
None defined yet.
Recent Activity
Papers
ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning
OVO-S-Bench: A Hierarchical Benchmark for Streaming Spatial Intelligence in Multimodal LLMs
-
InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
Paper • 2508.18265 • Published • 224 -
OpenGVLab/InternVL3_5-241B-A28B
Image-Text-to-Text • 241B • Updated • 786 • 139 -
OpenGVLab/InternVL3_5-38B
Image-Text-to-Text • 38B • Updated • 13.4k • 44 -
OpenGVLab/InternVL3_5-30B-A3B
Image-Text-to-Text • 31B • Updated • 80.3k • 43
-
internlm/internlm3-8b-instruct
Text Generation • 9B • Updated • 75.5k • 232 -
internlm/internlm3-8b-instruct-gguf
Text Generation • 9B • Updated • 236 • 28 -
internlm/internlm3-8b-instruct-awq
Text Generation • Updated • 534 • 6 -
internlm/internlm3-8b-instruct-gptq-int4
Text Generation • Updated • 24 • 4
Stimulating Dense Image Caption Capabilities via Reinforcement Learning
-
CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning
Paper • 2509.22647 • Published • 37 -
CapRL-Qwen3VL-4B for Image Captioning
🎨4Generate captions for images with CapRL-Qwen3VL-4B
-
internlm/CapRL-Qwen3VL-4B
Image-Text-to-Text • 4B • Updated • 859 • 12 -
internlm/CapRL-Qwen3VL-2B
Image-Text-to-Text • 2B • Updated • 157 • 14
-
internlm/OREAL-32B
Text Generation • Updated • 49 • 24 -
internlm/OREAL-7B
Text Generation • 8B • Updated • 50 • • 20 -
internlm/OREAL-DeepSeek-R1-Distill-Qwen-7B
Text Generation • 8B • Updated • 67 • 9 -
Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning
Paper • 2502.06781 • Published • 58
-
internlm/internlm-xcomposer2-4khd-7b
Visual Question Answering • Updated • 402 • 73 -
internlm/internlm-xcomposer2-vl-7b
Visual Question Answering • Updated • 719 • 84 -
internlm/internlm-xcomposer2-vl-1_8b
Visual Question Answering • Updated • 108 • 18 -
internlm/internlm-xcomposer2-7b
Text Generation • Updated • 8.66k • 31
Editing To Clarify and Harness Reasoning
-
JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence
Paper • 2510.23538 • Published • 99 -
internlm/JanusCoder-14B
Text Generation • 15B • Updated • 54 • • 34 -
internlm/JanusCoder-8B
Image-Text-to-Text • 8B • Updated • 48 • • 13 -
internlm/JanusCoderV-8B
Image-Text-to-Text • 9B • Updated • 131 • 13
InternLM2 Reward Models
-
internlm/internlm2-math-plus-20b
Text Generation • 20B • Updated • 88 • 7 -
internlm/internlm2-math-plus-7b
Text Generation • 8B • Updated • 266 • 11 -
internlm/internlm2-math-plus-1_8b
Text Generation • 2B • Updated • 196 • 12 -
internlm/internlm2-math-plus-mixtral8x22b
Text Generation • 141B • Updated • 41 • 19
-
InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
Paper • 2508.18265 • Published • 224 -
OpenGVLab/InternVL3_5-241B-A28B
Image-Text-to-Text • 241B • Updated • 786 • 139 -
OpenGVLab/InternVL3_5-38B
Image-Text-to-Text • 38B • Updated • 13.4k • 44 -
OpenGVLab/InternVL3_5-30B-A3B
Image-Text-to-Text • 31B • Updated • 80.3k • 43
Editing To Clarify and Harness Reasoning
-
internlm/internlm3-8b-instruct
Text Generation • 9B • Updated • 75.5k • 232 -
internlm/internlm3-8b-instruct-gguf
Text Generation • 9B • Updated • 236 • 28 -
internlm/internlm3-8b-instruct-awq
Text Generation • Updated • 534 • 6 -
internlm/internlm3-8b-instruct-gptq-int4
Text Generation • Updated • 24 • 4
-
JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence
Paper • 2510.23538 • Published • 99 -
internlm/JanusCoder-14B
Text Generation • 15B • Updated • 54 • • 34 -
internlm/JanusCoder-8B
Image-Text-to-Text • 8B • Updated • 48 • • 13 -
internlm/JanusCoderV-8B
Image-Text-to-Text • 9B • Updated • 131 • 13
Stimulating Dense Image Caption Capabilities via Reinforcement Learning
-
CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning
Paper • 2509.22647 • Published • 37 -
CapRL-Qwen3VL-4B for Image Captioning
🎨4Generate captions for images with CapRL-Qwen3VL-4B
-
internlm/CapRL-Qwen3VL-4B
Image-Text-to-Text • 4B • Updated • 859 • 12 -
internlm/CapRL-Qwen3VL-2B
Image-Text-to-Text • 2B • Updated • 157 • 14
-
internlm/OREAL-32B
Text Generation • Updated • 49 • 24 -
internlm/OREAL-7B
Text Generation • 8B • Updated • 50 • • 20 -
internlm/OREAL-DeepSeek-R1-Distill-Qwen-7B
Text Generation • 8B • Updated • 67 • 9 -
Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning
Paper • 2502.06781 • Published • 58
InternLM2 Reward Models
-
internlm/internlm2-math-plus-20b
Text Generation • 20B • Updated • 88 • 7 -
internlm/internlm2-math-plus-7b
Text Generation • 8B • Updated • 266 • 11 -
internlm/internlm2-math-plus-1_8b
Text Generation • 2B • Updated • 196 • 12 -
internlm/internlm2-math-plus-mixtral8x22b
Text Generation • 141B • Updated • 41 • 19
-
internlm/internlm-xcomposer2-4khd-7b
Visual Question Answering • Updated • 402 • 73 -
internlm/internlm-xcomposer2-vl-7b
Visual Question Answering • Updated • 719 • 84 -
internlm/internlm-xcomposer2-vl-1_8b
Visual Question Answering • Updated • 108 • 18 -
internlm/internlm-xcomposer2-7b
Text Generation • Updated • 8.66k • 31