Tiny static safety guards: multilabel moderation at wire speed on CPU
Robin Williams
bfuzzy1
AI & ML interests
all of the above.
Recent Activity
new activity 1 day ago
rl-llm-wiki/knowledge-base:source: arxiv:2305.00944 - Poisoning instruction tuningOrganizations
small language models
-
RobustFT: Robust Supervised Fine-tuning for Large Language Models under Noisy Response
Paper • 2412.14922 • Published • 87 -
B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners
Paper • 2412.17256 • Published • 47 -
Deliberation in Latent Space via Differentiable Cache Augmentation
Paper • 2412.17747 • Published • 32 -
Outcome-Refining Process Supervision for Code Generation
Paper • 2412.15118 • Published • 19
fine tuned models focused on veteran support
Collection of resources related to Agents.
-
Communicative Agents for Software Development
Paper • 2307.07924 • Published • 6 -
Self-Refine: Iterative Refinement with Self-Feedback
Paper • 2303.17651 • Published • 2 -
ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent
Paper • 2312.10003 • Published • 44 -
ReAct: Synergizing Reasoning and Acting in Language Models
Paper • 2210.03629 • Published • 36
local moderation models
acheron slms
AI for Good.
-
Automated Design of Agentic Systems
Paper • 2408.08435 • Published • 40 -
On the limits of agency in agent-based models
Paper • 2409.10568 • Published • 14 -
On the Diagram of Thought
Paper • 2409.10038 • Published • 13 -
DSBench: How Far Are Data Science Agents to Becoming Data Science Experts?
Paper • 2409.07703 • Published • 66
-
LLMs + Persona-Plug = Personalized LLMs
Paper • 2409.11901 • Published • 35 -
To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning
Paper • 2409.12183 • Published • 39 -
Chain of Thought Empowers Transformers to Solve Inherently Serial Problems
Paper • 2402.12875 • Published • 13 -
TPI-LLM: Serving 70B-scale LLMs Efficiently on Low-resource Edge Devices
Paper • 2410.00531 • Published • 33
Tiny static safety guards: multilabel moderation at wire speed on CPU
local moderation models
small language models
-
RobustFT: Robust Supervised Fine-tuning for Large Language Models under Noisy Response
Paper • 2412.14922 • Published • 87 -
B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners
Paper • 2412.17256 • Published • 47 -
Deliberation in Latent Space via Differentiable Cache Augmentation
Paper • 2412.17747 • Published • 32 -
Outcome-Refining Process Supervision for Code Generation
Paper • 2412.15118 • Published • 19
acheron slms
fine tuned models focused on veteran support
AI for Good.
Collection of resources related to Agents.
-
Communicative Agents for Software Development
Paper • 2307.07924 • Published • 6 -
Self-Refine: Iterative Refinement with Self-Feedback
Paper • 2303.17651 • Published • 2 -
ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent
Paper • 2312.10003 • Published • 44 -
ReAct: Synergizing Reasoning and Acting in Language Models
Paper • 2210.03629 • Published • 36
-
Automated Design of Agentic Systems
Paper • 2408.08435 • Published • 40 -
On the limits of agency in agent-based models
Paper • 2409.10568 • Published • 14 -
On the Diagram of Thought
Paper • 2409.10038 • Published • 13 -
DSBench: How Far Are Data Science Agents to Becoming Data Science Experts?
Paper • 2409.07703 • Published • 66
-
LLMs + Persona-Plug = Personalized LLMs
Paper • 2409.11901 • Published • 35 -
To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning
Paper • 2409.12183 • Published • 39 -
Chain of Thought Empowers Transformers to Solve Inherently Serial Problems
Paper • 2402.12875 • Published • 13 -
TPI-LLM: Serving 70B-scale LLMs Efficiently on Low-resource Edge Devices
Paper • 2410.00531 • Published • 33