LLMs + Persona-Plug = Personalized LLMs
Paper • 2409.11901 • Published • 35
Nifty
-
-
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 -
DiaSynth -- Synthetic Dialogue Generation Framework
Paper • 2409.19020 • Published • 20 -
ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs
Paper • 2410.12405 • Published • 13 -
What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective
Paper • 2410.23743 • Published • 64 -
SelfCodeAlign: Self-Alignment for Code Generation
Paper • 2410.24198 • Published • 25 -
BitStack: Fine-Grained Size Control for Compressed Large Language Models in Variable Memory Environments
Paper • 2410.23918 • Published • 21 -
ATM: Improving Model Merging by Alternating Tuning and Merging
Paper • 2411.03055 • Published • 1 -
OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models
Paper • 2411.04905 • Published • 128 -
Thanos: Enhancing Conversational Agents with Skill-of-Mind-Infused Large Language Model
Paper • 2411.04496 • Published • 22 -
Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding
Paper • 2411.04282 • Published • 37 -
Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens
Paper • 2411.17691 • Published • 13 -
Qwen2.5-Coder Technical Report
Paper • 2409.12186 • Published • 159 -
MALT: Improving Reasoning with Multi-Agent LLM Training
Paper • 2412.01928 • Published • 46 -
Wonderful Matrices: Combining for a More Efficient and Effective Foundation Model Architecture
Paper • 2412.11834 • Published • 8 -
Offline Reinforcement Learning for LLM Multi-Step Reasoning
Paper • 2412.16145 • Published • 38 -
ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing
Paper • 2412.14711 • Published • 16 -
RobustFT: Robust Supervised Fine-tuning for Large Language Models under Noisy Response
Paper • 2412.14922 • Published • 87 -
Analyze Feature Flow to Enhance Interpretation and Steering in Language Models
Paper • 2502.03032 • Published • 59 -
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
Paper • 2502.05171 • Published • 161 -
InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU
Paper • 2502.08910 • Published • 149 -
CoT-Valve: Length-Compressible Chain-of-Thought Tuning
Paper • 2502.09601 • Published • 14 -
SQuARE: Sequential Question Answering Reasoning Engine for Enhanced Chain-of-Thought in Large Language Models
Paper • 2502.09390 • Published • 15 -
Dyve: Thinking Fast and Slow for Dynamic Process Verification
Paper • 2502.11157 • Published • 7 -
Building A Proof-Oriented Programmer That Is 64% Better Than GPT-4o Under Data Scarsity
Paper • 2502.11901 • Published • 6 -
FoNE: Precise Single-Token Number Embeddings via Fourier Features
Paper • 2502.09741 • Published • 15 -
Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment
Paper • 2502.16894 • Published • 33 -
MeshPad: Interactive Sketch Conditioned Artistic-designed Mesh Generation and Editing
Paper • 2503.01425 • Published • 14 -
I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders
Paper • 2503.18878 • Published • 121 -
LogQuant: Log-Distributed 2-Bit Quantization of KV Cache with Superior Accuracy Preservation
Paper • 2503.19950 • Published • 12 -
TTRL: Test-Time Reinforcement Learning
Paper • 2504.16084 • Published • 123 -
Taming the Titans: A Survey of Efficient LLM Inference Serving
Paper • 2504.19720 • Published • 12 -
RM-R1: Reward Modeling as Reasoning
Paper • 2505.02387 • Published • 81 -
ReplaceMe: Network Simplification via Depth Pruning and Transformer Block Linearization
Paper • 2505.02819 • Published • 26 -
Delta Attention: Fast and Accurate Sparse Attention Inference by Delta Correction
Paper • 2505.11254 • Published • 49 -
Diffusion vs. Autoregressive Language Models: A Text Embedding Perspective
Paper • 2505.15045 • Published • 56 -
Shifting AI Efficiency From Model-Centric to Data-Centric Compression
Paper • 2505.19147 • Published • 146 -
Scaling Laws for Optimal Data Mixtures
Paper • 2507.09404 • Published • 39 -
FLEXITOKENS: Flexible Tokenization for Evolving Language Models
Paper • 2507.12720 • Published • 10 -
Weak-Driven Learning: How Weak Agents make Strong Agents Stronger
Paper • 2602.08222 • Published • 290 -
Agents of Chaos
Paper • 2602.20021 • Published • 36 -
Fast Weight Attention for Continual Learning
Paper • 2608.27763 • Published • 23