-
Agents: An Open-source Framework for Autonomous Language Agents
Paper • 2309.07870 • Published • 42 -
More Agents Is All You Need
Paper • 2402.05120 • Published • 58 -
Tag-LLM: Repurposing General-Purpose LLMs for Specialized Domains
Paper • 2402.05140 • Published • 24 -
ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent
Paper • 2312.10003 • Published • 44
Jian Liao
imjliao
AI & ML interests
None yet
Recent Activity
liked
a model
12 days ago
ChatDOC/OCRFlux-3B
liked
a model
12 days ago
microsoft/VibeVoice-1.5B
upvoted
a
paper
about 1 month ago
Beyond Context Limits: Subconscious Threads for Long-Horizon Reasoning
Organizations
Reasoning
-
Iterated Decomposition: Improving Science Q&A by Supervising Reasoning Processes
Paper • 2301.01751 • Published -
Question Decomposition Improves the Faithfulness of Model-Generated Reasoning
Paper • 2307.11768 • Published • 13 -
Contrastive Decoding Improves Reasoning in Large Language Models
Paper • 2309.09117 • Published • 39 -
Skeleton-of-Thought: Large Language Models Can Do Parallel Decoding
Paper • 2307.15337 • Published • 38
Synthetic Data
Data enrichment methods for pre-training and fine-tuning
-
Adapting Large Language Models via Reading Comprehension
Paper • 2309.09530 • Published • 81 -
RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
Paper • 2309.00267 • Published • 52 -
Self-Alignment with Instruction Backtranslation
Paper • 2308.06259 • Published • 42 -
Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor
Paper • 2212.09689 • Published • 1
Entity
QA
Long Context
Tool Use
MLLM
-
Question Aware Vision Transformer for Multimodal Reasoning
Paper • 2402.05472 • Published • 10 -
ScreenAI: A Vision-Language Model for UI and Infographics Understanding
Paper • 2402.04615 • Published • 45 -
WebLINX: Real-World Website Navigation with Multi-Turn Dialogue
Paper • 2402.05930 • Published • 40 -
More Agents Is All You Need
Paper • 2402.05120 • Published • 58
Models
-
JetMoE: Reaching Llama2 Performance with 0.1M Dollars
Paper • 2404.07413 • Published • 39 -
Rho-1: Not All Tokens Are What You Need
Paper • 2404.07965 • Published • 94 -
Jamba: A Hybrid Transformer-Mamba Language Model
Paper • 2403.19887 • Published • 112 -
Mixture-of-Depths: Dynamically allocating compute in transformer-based language models
Paper • 2404.02258 • Published • 108
Summarization
Prompt
Papers related to prompt engineering and optimizers
-
Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers
Paper • 2309.08532 • Published • 53 -
Large Language Models as Optimizers
Paper • 2309.03409 • Published • 77 -
Graph of Thoughts: Solving Elaborate Problems with Large Language Models
Paper • 2308.09687 • Published • 7 -
Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks
Paper • 2211.12588 • Published • 3
Dialogue
Information Retrieval
Document Information Extraction
Document AI
Fine Tuning
-
Tuna: Instruction Tuning using Feedback from Large Language Models
Paper • 2310.13385 • Published • 10 -
Contrastive Prefence Learning: Learning from Human Feedback without RL
Paper • 2310.13639 • Published • 25 -
Teaching Language Models to Self-Improve through Interactive Demonstrations
Paper • 2310.13522 • Published • 12 -
Zephyr: Direct Distillation of LM Alignment
Paper • 2310.16944 • Published • 122
AIF
Agent
-
Agents: An Open-source Framework for Autonomous Language Agents
Paper • 2309.07870 • Published • 42 -
More Agents Is All You Need
Paper • 2402.05120 • Published • 58 -
Tag-LLM: Repurposing General-Purpose LLMs for Specialized Domains
Paper • 2402.05140 • Published • 24 -
ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent
Paper • 2312.10003 • Published • 44
Summarization
Reasoning
-
Iterated Decomposition: Improving Science Q&A by Supervising Reasoning Processes
Paper • 2301.01751 • Published -
Question Decomposition Improves the Faithfulness of Model-Generated Reasoning
Paper • 2307.11768 • Published • 13 -
Contrastive Decoding Improves Reasoning in Large Language Models
Paper • 2309.09117 • Published • 39 -
Skeleton-of-Thought: Large Language Models Can Do Parallel Decoding
Paper • 2307.15337 • Published • 38
Prompt
Papers related to prompt engineering and optimizers
-
Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers
Paper • 2309.08532 • Published • 53 -
Large Language Models as Optimizers
Paper • 2309.03409 • Published • 77 -
Graph of Thoughts: Solving Elaborate Problems with Large Language Models
Paper • 2308.09687 • Published • 7 -
Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks
Paper • 2211.12588 • Published • 3
Synthetic Data
Data enrichment methods for pre-training and fine-tuning
-
Adapting Large Language Models via Reading Comprehension
Paper • 2309.09530 • Published • 81 -
RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
Paper • 2309.00267 • Published • 52 -
Self-Alignment with Instruction Backtranslation
Paper • 2308.06259 • Published • 42 -
Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor
Paper • 2212.09689 • Published • 1
Dialogue
Entity
Information Retrieval
QA
Document Information Extraction
Long Context
Document AI
Tool Use
Fine Tuning
-
Tuna: Instruction Tuning using Feedback from Large Language Models
Paper • 2310.13385 • Published • 10 -
Contrastive Prefence Learning: Learning from Human Feedback without RL
Paper • 2310.13639 • Published • 25 -
Teaching Language Models to Self-Improve through Interactive Demonstrations
Paper • 2310.13522 • Published • 12 -
Zephyr: Direct Distillation of LM Alignment
Paper • 2310.16944 • Published • 122
MLLM
-
Question Aware Vision Transformer for Multimodal Reasoning
Paper • 2402.05472 • Published • 10 -
ScreenAI: A Vision-Language Model for UI and Infographics Understanding
Paper • 2402.04615 • Published • 45 -
WebLINX: Real-World Website Navigation with Multi-Turn Dialogue
Paper • 2402.05930 • Published • 40 -
More Agents Is All You Need
Paper • 2402.05120 • Published • 58
AIF
Models
-
JetMoE: Reaching Llama2 Performance with 0.1M Dollars
Paper • 2404.07413 • Published • 39 -
Rho-1: Not All Tokens Are What You Need
Paper • 2404.07965 • Published • 94 -
Jamba: A Hybrid Transformer-Mamba Language Model
Paper • 2403.19887 • Published • 112 -
Mixture-of-Depths: Dynamically allocating compute in transformer-based language models
Paper • 2404.02258 • Published • 108