large language model
A type of AI model trained on vast amounts of text data to understand and generate human language. These models are capable of performing various natural language processing tasks, such as translation, summarization, and conversational agents, due to their deep architectures and extensive training.
- ALMGuard: Safety Shortcuts and Where to Find Them as Guardrails for Audio–Language Models
- Alignment of Large Language Models with Constrained Learning
- All You Need is One: Capsule Prompt Tuning with a Single Vector
- AutoData: A Multi-Agent System for Open Web Data Collection
- AutoJudge: Judge Decoding Without Manual Annotation
- Beyond Value Functions: Single-Loop Bilevel Optimization under Flatness Conditions
- BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model
- Bridging Sign and Spoken Languages: Pseudo Gloss Generation for Sign Language Translation
- ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive
- Codifying Character Logic in Role-Playing
- Conditional Representation Learning for Customized Tasks
- Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning
- Disentangled Concepts Speak Louder Than Words: Explainable Video Action Recognition
- DynaPipe: Dynamic Layer Redistribution for Efficient Serving of LLMs with Pipeline Parallelism
- E2E-VGuard: Adversarial Prevention for Production LLM-based End-To-End Speech Synthesis
- EasySpec: Layer-Parallel Speculative Decoding for Efficient Multi-GPU Utilization
- Enhancing Multilingual LLM Pretraining with Model-Based Data Selection
- Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia
- Guard Me If You Know Me: Protecting Specific Face-Identity from Deepfakes
- Hierarchical Optimization via LLM-Guided Objective Evolution for Mobility-on-Demand Systems
- How to Train Your LLM Web Agent: A Statistical Diagnosis
- Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections
- Influence Guided Context Selection for Effective Retrieval-Augmented Generation
- KScope: A Framework for Characterizing the Knowledge Status of Language Models
- LLM-DAMVC: A Large Language Model Assisted Dynamic Agent for Multi-View Clustering
- Large Language Bayes
- Learned Prefix Caching for Efficient LLM Inference
- LongVPO: From Anchored Cues to Self-Reasoning for Long-Form Video Preference Optimization
- Majority of the Bests: Improving Best-of-N via Bootstrapping
- MeCeFO: Enhancing LLM Training Robustness via Fault-Tolerant Optimization
- MedChain: Bridging the Gap Between LLM Agents and Clinical Practice with Interactive Sequence
- MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO
- NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache
- OpenOmni: Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-time Emotional Speech Synthesis
- Partition to Evolve: Niching-enhanced Evolution with LLMs for Automated Algorithm Discovery
- Polar Sparsity: High Throughput Batched LLM Inferencing with Scalable Contextual Sparsity
- Post Hoc Regression Refinement via Pairwise Rankings
- Preserving LLM Capabilities through Calibration Data Curation: From Analysis to Optimization
- Prompted Policy Search: Reinforcement Learning through Linguistic and Numerical Reasoning in LLMs
- Q-Palette: Fractional-Bit Quantizers Toward Optimal Bit Allocation for Efficient LLM Deployment
- REGen: Multimodal Retrieval-Embedded Generation for Long-to-Short Video Editing
- RESAnything: Attribute Prompting for Arbitrary Referring Segmentation
- ReDit: Reward Dithering for Improved LLM Policy Optimization
- Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective
- SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agents
- SGAR: Structural Generative Augmentation for 3D Human Motion Retrieval
- SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning
- Scaling Laws for Optimal Data Mixtures
- SceneForge: Enhancing 3D-text alignment with Structured Scene Compositions
- Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
- Storyboard-guided Alignment for Fine-grained Video Action Recognition
- SuffixDecoding: Extreme Speculative Decoding for Emerging AI Applications
- SymRTLO: Enhancing RTL Code Optimization with LLMs and Neuron-Inspired Symbolic Reasoning
- Token Embeddings Violate the Manifold Hypothesis
- Transcending Cost-Quality Tradeoff in Agent Serving via Session-Awareness
- TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets
- Universal Cross-Tokenizer Distillation via Approximate Likelihood Matching
- VLMLight: Safety-Critical Traffic Signal Control via Vision-Language Meta-Control and Dual-Branch Reasoning Architecture
- Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations
- Vision‑Language‑Vision Auto‑Encoder: Scalable Knowledge Distillation from Diffusion Models
- Who You Are Matters: Bridging Interests and Social Roles via LLM-Enhanced Logic Recommendation
- scPilot: Large Language Model Reasoning Toward Automated Single-Cell Analysis and Discovery