shane are
arionsingul
AI & ML interests
None yet
Recent Activity
liked
a model
10 days ago
moonshotai/Kimi-K2-Base
liked
a Space
22 days ago
LLM360/de-arena
liked
a Space
about 1 month ago
osunlp/Online_Mind2Web_Leaderboard
Organizations
-
Beyond ChatBots: ExploreLLM for Structured Thoughts and Personalized Model Responses
Paper β’ 2312.00763 β’ Published β’ 22 -
EmerDiff: Emerging Pixel-level Semantic Knowledge in Diffusion Models
Paper β’ 2401.11739 β’ Published β’ 17 -
Beyond Natural Language: LLMs Leveraging Alternative Formats for Enhanced Reasoning and Communication
Paper β’ 2402.18439 β’ Published β’ 1
Coding
-
CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation
Paper β’ 2311.08588 β’ Published -
OpenGVLab/InternVL-Chat-V1-5
Image-Text-to-Text β’ 26B β’ Updated β’ 3.16k β’ 411 -
OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models
Paper β’ 2411.04905 β’ Published β’ 126
-
Edify 3D: Scalable High-Quality 3D Asset Generation
Paper β’ 2411.07135 β’ Published -
LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations
Paper β’ 2410.02707 β’ Published β’ 49 -
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
Paper β’ 2502.05171 β’ Published β’ 144
-
Beyond ChatBots: ExploreLLM for Structured Thoughts and Personalized Model Responses
Paper β’ 2312.00763 β’ Published β’ 22 -
EmerDiff: Emerging Pixel-level Semantic Knowledge in Diffusion Models
Paper β’ 2401.11739 β’ Published β’ 17 -
Beyond Natural Language: LLMs Leveraging Alternative Formats for Enhanced Reasoning and Communication
Paper β’ 2402.18439 β’ Published β’ 1
Coding
-
CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation
Paper β’ 2311.08588 β’ Published -
OpenGVLab/InternVL-Chat-V1-5
Image-Text-to-Text β’ 26B β’ Updated β’ 3.16k β’ 411 -
OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models
Paper β’ 2411.04905 β’ Published β’ 126
-
Edify 3D: Scalable High-Quality 3D Asset Generation
Paper β’ 2411.07135 β’ Published -
LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations
Paper β’ 2410.02707 β’ Published β’ 49 -
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
Paper β’ 2502.05171 β’ Published β’ 144