Efficient Differentially Private Fine-Tuning of LLMs via Reinforcement Learning
arxiv.org·3d
🔧Systems-level optimizations for LLM serving
Optimizing LLMs for Performance and Accuracy with Post-Training Quantization
developer.nvidia.com·3d
🔢Quantization of LLMs
Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey
arxiv.org·2d
🧠Large Language Models (LLMs)
LENS: Learning Ensemble Confidence from Neural States for Multi-LLM Answer Integration
arxiv.org·2d
🧠Large Language Models (LLMs)
LLM-Crowdsourced: A Benchmark-Free Paradigm for Mutual Evaluation of Large Language Models
arxiv.org·3d
🧠Large Language Models (LLMs)
Tensor-based reduction of linear parameter-varying state-space models
arxiv.org·2d
🔢Quantization of LLMs
Improving annotator selection in Active Learning using a mood and fatigue-aware Recommender System
arxiv.org·2d
🧠Large Language Models (LLMs)
Formal Bayesian Transfer Learning via the Total Risk Prior
arxiv.org·2d
🧠Large Language Models (LLMs)
FairReason: Balancing Reasoning and Social Bias in MLLMs
arxiv.org·2d
🧠Large Language Models (LLMs)
From Sufficiency to Reflection: Reinforcement-Guided Thinking Quality in Retrieval-Augmented Reasoning for LLMs
arxiv.org·3d
🔍Retrieval-augmented generation
LoRA-PAR: A Flexible Dual-System LoRA Partitioning Approach to Efficient LLM Fine-Tuning
arxiv.org·5d
🧠Large Language Models (LLMs)
RL from Teacher-Model Refinement: Gradual Imitation Learning for Machine Translation
arxiv.org·3d
🧠Large Language Models (LLMs)
Tropical solution of discrete best approximation problems
arxiv.org·3d
🔢Quantization of LLMs
Exploiting Synergistic Cognitive Biases to Bypass Safety in LLMs
arxiv.org·3d
🧠Large Language Models (LLMs)
Good Learners Think Their Thinking: Generative PRM Makes Large Reasoning Model More Efficient Math Learner
arxiv.org·2d
🧠Large Language Models (LLMs)
Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes
arxiv.org·2d
🧠Large Language Models (LLMs)
Uncovering the Fragility of Trustworthy LLMs through Chinese Textual Ambiguity
arxiv.org·2d
🧠Large Language Models (LLMs)
AI paradigm for solving differential equations: first-principles data generation and scale-dilation operator AI solver
arxiv.org·2d
📊AI Performance Profiling
Federated Distributionally Robust Optimization with Non-Convex Objectives: Algorithm and Analysis
arxiv.org·3d
🔧Systems-level optimizations for LLM serving
A Scalable Pipeline for Estimating Verb Frame Frequencies Using Large Language Models
arxiv.org·3d
🧠Large Language Models (LLMs)