AtP*: An efficient and scalable method for localizing LLM behaviour to components
Paper
• 2403.00745 • Published
• 14
Interesting
Interesting things.
-
-
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
Paper • 2402.17764 • Published • 627 -
MobiLlama: Towards Accurate and Lightweight Fully Transparent GPT
Paper • 2402.16840 • Published • 25 -
LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens
Paper • 2402.13753 • Published • 116 -
AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling
Paper • 2402.12226 • Published • 45 -
Learning to Learn Faster from Human Feedback with Language Model Predictive Control
Paper • 2402.11450 • Published • 22 -
HeadStudio: Text to Animatable Head Avatars with 3D Gaussian Splatting
Paper • 2402.06149 • Published • 18 -
CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay
Paper • 2402.04858 • Published • 15 -
Self-Discover: Large Language Models Self-Compose Reasoning Structures
Paper • 2402.03620 • Published • 117 -
Rethinking Optimization and Architecture for Tiny Language Models
Paper • 2402.02791 • Published • 13 -
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Paper • 2402.03300 • Published • 141 -
LongAlign: A Recipe for Long Context Alignment of Large Language Models
Paper • 2401.18058 • Published • 24 -
MoE-LLaVA: Mixture of Experts for Large Vision-Language Models
Paper • 2401.15947 • Published • 53 -
AutoRT: Embodied Foundation Models for Large Scale Orchestration of Robotic Agents
Paper • 2401.12963 • Published • 12 -
Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding
Paper • 2401.12954 • Published • 33 -
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
Paper • 2401.10774 • Published • 59 -
Transformers are Multi-State RNNs
Paper • 2401.06104 • Published • 39 -
Learning to Decode Collaboratively with Multiple Language Models
Paper • 2403.03870 • Published • 21 -
LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error
Paper • 2403.04746 • Published • 24 -
PERL: Parameter Efficient Reinforcement Learning from Human Feedback
Paper • 2403.10704 • Published • 60 -
Larimar: Large Language Models with Episodic Memory Control
Paper • 2403.11901 • Published • 33 -
Alignment Studio: Aligning Large Language Models to Particular Contextual Regulations
Paper • 2403.09704 • Published • 32 -
Recurrent Drafter for Fast Speculative Decoding in Large Language Models
Paper • 2403.09919 • Published • 21 -
The Unreasonable Ineffectiveness of the Deeper Layers
Paper • 2403.17887 • Published • 82 -
Transformer-Lite: High-efficiency Deployment of Large Language Models on Mobile Phone GPUs
Paper • 2403.20041 • Published • 34 -
Simple and Scalable Strategies to Continually Pre-train Large Language Models
Paper • 2403.08763 • Published • 51 -
Mixture-of-Depths: Dynamically allocating compute in transformer-based language models
Paper • 2404.02258 • Published • 107 -
Chronos: Learning the Language of Time Series
Paper • 2403.07815 • Published • 48 -
MoAI: Mixture of All Intelligence for Large Language and Vision Models
Paper • 2403.07508 • Published • 77 -
Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM
Paper • 2403.07816 • Published • 44 -
V3D: Video Diffusion Models are Effective 3D Generators
Paper • 2403.06738 • Published • 30 -
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
Paper • 2403.03507 • Published • 189 -
BLINK: Multimodal Large Language Models Can See but Not Perceive
Paper • 2404.12390 • Published • 26 -
FLAME: Factuality-Aware Alignment for Large Language Models
Paper • 2405.01525 • Published • 29 -
Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models
Paper • 2405.01535 • Published • 124 -
Self-Play Preference Optimization for Language Model Alignment
Paper • 2405.00675 • Published • 28 -
Better & Faster Large Language Models via Multi-token Prediction
Paper • 2404.19737 • Published • 81 -
GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting
Paper • 2404.19702 • Published • 20 -
XC-Cache: Cross-Attending to Cached Context for Efficient LLM Inference
Paper • 2404.15420 • Published • 11 -
RLHF Workflow: From Reward Modeling to Online RLHF
Paper • 2405.07863 • Published • 71 -
Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
Paper • 2405.12981 • Published • 33 -
Towards Modular LLMs by Building and Reusing a Library of LoRAs
Paper • 2405.11157 • Published • 31 -
Not All Language Model Features Are Linear
Paper • 2405.14860 • Published • 40 -
Instruct-MusicGen: Unlocking Text-to-Music Editing for Music Language Models via Instruction Tuning
Paper • 2405.18386 • Published • 22 -
Similarity is Not All You Need: Endowing Retrieval Augmented Generation with Multi Layered Thoughts
Paper • 2405.19893 • Published • 33 -
OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework
Paper • 2405.11143 • Published • 41 -
An Introduction to Vision-Language Modeling
Paper • 2405.17247 • Published • 90 -
ALPINE: Unveiling the Planning Capability of Autoregressive Learning in Language Models
Paper • 2405.09220 • Published • 27 -
Understanding the performance gap between online and offline alignment algorithms
Paper • 2405.08448 • Published • 18 -
TrustLLM: Trustworthiness in Large Language Models
Paper • 2401.05561 • Published • 69 -
DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
Paper • 2401.06066 • Published • 59 -
Patchscope: A Unifying Framework for Inspecting Hidden Representations of Language Models
Paper • 2401.06102 • Published • 22 -
Secrets of RLHF in Large Language Models Part II: Reward Modeling
Paper • 2401.06080 • Published • 28 -
TRIPS: Trilinear Point Splatting for Real-Time Radiance Field Rendering
Paper • 2401.06003 • Published • 25 -
Understanding LLMs: A Comprehensive Overview from Training to Inference
Paper • 2401.02038 • Published • 65 -
One-dimensional Adapter to Rule Them All: Concepts, Diffusion Models and Erasing Applications
Paper • 2312.16145 • Published • 10 -
Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models
Paper • 2312.13913 • Published • 24 -
Splatter Image: Ultra-Fast Single-View 3D Reconstruction
Paper • 2312.13150 • Published • 15 -
Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models
Paper • 2312.13763 • Published • 10 -
Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model
Paper • 2312.12423 • Published • 13 -
LIME: Localized Image Editing via Attention Regularization in Diffusion Models
Paper • 2312.09256 • Published • 10 -
FreeInit: Bridging Initialization Gap in Video Diffusion Models
Paper • 2312.07537 • Published • 27 -
GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning
Paper • 2312.11461 • Published • 20 -
VecFusion: Vector Font Generation with Diffusion
Paper • 2312.10540 • Published • 22 -
Reka Core, Flash, and Edge: A Series of Powerful Multimodal Language Models
Paper • 2404.12387 • Published • 39 -
Distributed Inference and Fine-tuning of Large Language Models Over The Internet
Paper • 2312.08361 • Published • 27 -
PromptBench: A Unified Library for Evaluation of Large Language Models
Paper • 2312.07910 • Published • 16 -
LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes
Paper • 2311.13384 • Published • 53 -
A Framework for Automated Measurement of Responsible AI Harms in Generative AI Applications
Paper • 2310.17750 • Published • 9 -
ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search
Paper • 2310.13227 • Published • 15 -
ControlLLM: Augment Language Models with Tools by Searching on Graphs
Paper • 2310.17796 • Published • 18 -
CodeFusion: A Pre-trained Diffusion Model for Code Generation
Paper • 2310.17680 • Published • 74 -
Wonder3D: Single Image to 3D using Cross-Domain Diffusion
Paper • 2310.15008 • Published • 22 -
Woodpecker: Hallucination Correction for Multimodal Large Language Models
Paper • 2310.16045 • Published • 17 -
Safe RLHF: Safe Reinforcement Learning from Human Feedback
Paper • 2310.12773 • Published • 28 -
3D-GPT: Procedural 3D Modeling with Large Language Models
Paper • 2310.12945 • Published • 61 -
BitNet: Scaling 1-bit Transformers for Large Language Models
Paper • 2310.11453 • Published • 106 -
Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Models
Paper • 2308.00675 • Published • 37