fangyuan-ksgk
AI Engineer (LLM) @Temus || Artificial Intelligence Student @Stanford
@Temus-AISingapore
Pinned Repositories
CoT-Reasoning-without-Prompting
Unofficial Implementation of Chain-of-Thought Reasoning Without Prompting
Evolutionary-Model-Merge
Unofficial Implementation of Evolutionary Model Merging
Iterative_graph_alignment
Official Implementation of Iterative Graph Alignment https://arxiv.org/abs/2408.16667
llama3-sft
Supervised FineTuning with Llama-3
Mini-LLaVA
A minimal implementation of LLaVA-style VLM with interleaved image & text & video processing ability.
paper-read-2024-Jan-Apr
Paper reading run from 17. Jan 2024 - 17. Apr 2024
repo-viewer
Visualize any repo or codebase into diagram or animation
RuleAlign
Rule-Based Adherance evaluation for LLM Agent
selective-attention-transformer
Unofficial Implementation of Selective Attention Transformer
STaR
Implementation of STaR: Bootstrapping Reasoning With Reasoning
fangyuan-ksgk's Repositories
fangyuan-ksgk/Mini-LLaVA
A minimal implementation of LLaVA-style VLM with interleaved image & text & video processing ability.
fangyuan-ksgk/selective-attention-transformer
Unofficial Implementation of Selective Attention Transformer
fangyuan-ksgk/Iterative_graph_alignment
Official Implementation of Iterative Graph Alignment https://arxiv.org/abs/2408.16667
fangyuan-ksgk/concept-encoding
experiment with concept encoding in LLM
fangyuan-ksgk/diamond
DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.
fangyuan-ksgk/adaptive-length-tokenizer
Adaptive Length Image Tokenization via Recurrent Allocation | How many tokens is an image worth ?
fangyuan-ksgk/agent.exe
fangyuan-ksgk/ai-hedge-fund
An AI Hedge Fund Team
fangyuan-ksgk/BALROG
Benchmarking Agentic LLM and VLM Reasoning On Games
fangyuan-ksgk/brain-tokyo-workshop
🧠🗼
fangyuan-ksgk/convex-splatting
Original implementation of "3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes"
fangyuan-ksgk/diffuse-experiment
Experiment on Diffusion world model (Collaborate with Devin)
fangyuan-ksgk/distill-experiment
Experiment on distillation
fangyuan-ksgk/fangyuan-ksgk
github page
fangyuan-ksgk/front-end-test
Test with front end automation tools
fangyuan-ksgk/iAgents
Fork iAgent framework for exploring multi-agent front-end environment
fangyuan-ksgk/ICL_Modular_Arithmetic
nice baseline experiemnt for "grokking"
fangyuan-ksgk/neurips2024-inference-tutorial-code
Grindint on inference tutorial from NeurIPS
fangyuan-ksgk/open-oasis
Inference script for Oasis 500M
fangyuan-ksgk/screenshot-to-code
Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)
fangyuan-ksgk/SeeAct
[ICML'24] SeeAct is a system for generalist web agents that autonomously carry out tasks on any given website, with a focus on large multimodal models (LMMs) such as GPT-4V(ision).
fangyuan-ksgk/servers
Model Context Protocol Servers
fangyuan-ksgk/SlimeBall
Port of SlimeVolleyBall environment
fangyuan-ksgk/slimevolleygym
A simple OpenAI Gym environment for single and multi-agent reinforcement learning
fangyuan-ksgk/soar
Code release for paper "Autonomous Improvement of Instruction Following Skills via Foundation Models" | CoRL 2024
fangyuan-ksgk/SUPE
This code accompanies the paper "Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration."
fangyuan-ksgk/SWE-Gym
Test with SWE-Gym environment
fangyuan-ksgk/tiktok-clone
fangyuan-ksgk/Trace
End-to-end Generative Optimization for AI Agents
fangyuan-ksgk/unit
Next Generation Visual Programming System