LLM papers in NeurIPS 2024
(Abstracts and arxiv links will be uploaded soon.)
| Title |
|---|
| Improving Sparse Decomposition of Language Model Activations with Gated Sparse Autoencoders |
| IDGen: Item Discrimination Induced Prompt Generation for LLM Evaluation |
| Toward a Stable, Fair, and Comprehensive Evaluation of Object Hallucination in Large Vision-Language Models |
| Exploring Context Window of Large Language Models via Decomposed Positional Vectors |
| FLAME : Factuality-Aware Alignment for Large Language Models |
| Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses |
| Mesa-Extrapolation: A Weave Position Encoding Method for Enhanced Extrapolation in LLMs |
| Aligning Large Language Models with Representation Editing: A Control Perspective |
| GTBench: Uncovering the Strategic Reasoning Capabilities of LLMs via Game-Theoretic Evaluations |
| Alignment at Pre-training! Towards Native Alignment for Arabic LLMs |
| Automated Multi-level Preference for MLLMs |
| DDK: Distilling Domain Knowledge for Efficient Large Language Models |
| LLM-ESR: Large Language Models Enhancement for Long-tailed Sequential Recommendation |
| Efficient Contextual LLM Cascades through Budget-Constrained Policy Learning |
| Does Reasoning Emerge? Examining the Probabilities of Causation in Large Language Models |
| Advancing Cross-domain Discriminability in Continual Learning of Vison-Language Models |
| Text-Guided Attention is All You Need for Zero-Shot Robustness in Vision-Language Models |
| InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory |
| Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control |
| UMFC: Unsupervised Multi-Domain Feature Calibration for Vision-Language Models |
| Never Miss A Beat: An Efficient Recipe for Context Window Extension of Large Language Models with Consistent “Middle” Enhancement |
| Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models |
| Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models |
| Lever LM: Configuring In-Context Sequence to Lever Large Vision Language Models |
| Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models |
| MoGU: A Framework for Enhancing Safety of Open-Sourced LLMs While Preserving Their Usability |
| Tree of Attacks: Jailbreaking Black-Box LLMs Automatically |
| Learning Goal-Conditioned Representations in Reward Models for Aligning Language Models |
| Unveiling Encoder-Free Vision-Language Models |
| SpeechAlign: Speech Language Models Can Self-Improve via Preference Optimization |
| Multimodal Large Language Models Make Text-to-Image Generative Models Align Better |
| SpecExec: Massively Parallel Speculative Decoding For Interactive LLM Inference on Consumer Devices |
| Human-Readable Fingerprint for Large Language Models |
| Mixture of In-Context Experts Enhance LLMs' Long Context Awareness |
| Alleviating Hallucinations in Large Vision-Language Models through Hallucination-Induced Optimization |
| Leveraging Environment Interaction for Automated PDDL Generation and Planning with Large Language Models |
| LACIE: Listener-Aware Finetuning for Calibration in Large Language Models |
| Large language model validity via enhanced conformal prediction methods |
| Exploiting LLM Quantization |
| Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models |
| Understanding Emergent Abilities of Language Models from the Loss Perspective |
| LLM Circuit Analyses Are Consistent Across Training and Scale |
| Boosting Text-to-Video Generative Model with MLLMs Feedback |
| Visual Anchors Are Strong Information Aggregators For Multimodal Large Language Model |
| You Only Cache Once: Decoder-Decoder Architectures for Language Models |
| Delving into the Reversal Curse: How Far Can Large Language Models Generalize? |
| ProSST: Protein Language Modeling with Quantized Structure and Disentangled Attention |
| Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generation |
| LLM Evaluators Recognize and Favor Their Own Generations |
| Distributional Preference Alignment of LLMs via Optimal Transport |
| Risk-Averse Finetuning of Large Language Models |
| Truth is Universal: Robust Detection of Lies in LLMs |
| Large Language Models as Hyper-Heuristics for Combinatorial Optimization |
| Rethinking Memory and Communication Costs for Efficient Large Language Model Training |
| EvolveDirector: Approaching Advanced Text-to-Image Generation with Large Vision-Language Models |
| AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment |
| Compute-efficient LLM Training via Online Batch Selection |
| Can LLMs Learn by Teaching? A Preliminary Study |
| Understanding Linear Probing then Fine-tuning Language Models from NTK Perspective |
| TableRAG: Million-Token Tabular Reasoning with Large Language Models |
| iVideoGPT: Interactive VideoGPTs are Scalable World Models |
| Linguistic Collapse: Neural Collapse in (Large) Language Models |
| Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs |
| Diffusion of Thought: Chain-of-Thought Reasoning in Diffusion Language Models |
| Decoding-Time Language Model Alignment with Multiple Objectives |
| Confidence Regulation Neurons in Language Models |
| Approaching Human-Level Forecasting with Language Models |
| BAdam: A Memory Efficient Full Parameter Optimization Method for Large Language Models |
| Mobility-LLM: Learning Visiting Intentions and Travel Preference from Human Mobility Data with Large Language Models |
| KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization |
| ALPS: Improved Optimization for Highly Sparse One-Shot Pruning for Large Language Models |
| LLMs as Zero-shot Graph Learners: Alignment of GNN Represetantions with LLM Token Embeddings |
| Long-form factuality in large language models |
| Cooperate or Collapse: Emergence of Sustainability in a Society of LLM Agents |
| AutoTimes: Autoregressive Time Series Forecasters via Large Language Models |
| Probing the Decision Boundaries of In-context Learning in Large Language Models |
| Bridge the Modality and Capacity Gaps in Vision-Language Model Selection |
| A Unified Debiasing Approach for Vision-Language Models across Modalities and Tasks |
| Unleash Region Understanding in Intermediate Layers for MLLM-based Referring Expression Generation |
| A Critical Evaluation of AI Feedback for Aligning Large Language Models |
| Enhancing Large Language Models through Adaptive Tokenizers |
| Adversarial Moment-Matching Distillation of Large Language Models |
| LLM Dataset Inference: Detect Datasets, not Strings |
| MAGNET: Improving the Multilingual Fairness of Language Models with Adaptive Gradient-Based Tokenization |
| Unveiling Causal Reasoning in Large Language Models: Reality or Mirage? |
| Are Language Models Actually Useful for Time Series Forecasting? |
| Grounding Multimodal Large Language Models in Actions |
| Invariant Tokenization for Language Model Enabled Crystal Materials Generation |
| FlowLLM: Flow Matching for Material Generation with Learned Base Distributions |
| When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search |
| SlowFocus: Enhancing Fine-grained Temporal Understanding in Video LLM |
| Resolving Discrepancies in Compute-Optimal Scaling of Language Models |
| Enhancing Large Vision Language Models with Self-Training on Image Comprehension |
| AutoSurvey: Large Language Models Can Automatically Write Surveys |
| Stacking Your Transformers: A Closer Look at Model Growth for Efficient LLM Pre-Training |
| Segmenting Watermarked Texts From Language Models |
| The Best of Both Worlds: Toward an Honest and Helpful Large Language Model |
| Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs |
| MDAgents: An Adaptive Collaboration of LLMs for Medical Decision Making |
| Divergences between Language Models and Human Brains |
| GPT as Visual Explainer |
| QuanTA: Efficient High-Rank Fine-Tuning of LLMs with Quantum-Informed Tensor Adaptation |
| Aligning LLM Agents by Learning Latent Preference from User Edits |
| IDGen: Item Discrimination Induced Prompt Generation for LLM Evaluation |
| Toward a Stable, Fair, and Comprehensive Evaluation of Object Hallucination in Large Vision-Language Models |
| MutaPLM: Protein Language Modeling for Mutation Explanation and Engineering |
| DDK: Distilling Domain Knowledge for Efficient Large Language Models |
| Interpreting Learned Feedback Patterns in Large Language Models |
| Is Programming by Example solved by LLMs? |
| LLM-ESR: Large Language Models Enhancement for Long-tailed Sequential Recommendation |
| Co-occurrence is not Factual Association in Language Models |
| Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates |
| RestoreAgent: Autonomous Image Restoration Agent via Multimodal Large Language Models |
| Prompting LLMs for Social Relation Reasoning via Greedy Segment Optimization |
| MediQ: Question-Asking LLMs for Adaptive and Reliable Medical Reasoning |
| A Decision-Language Model (DLM) for Dynamic Restless Multi-Armed Bandit Tasks in Public Health |
| StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving |
| Uncovering Safety Risks of Large Language Models through Concept Activation Vector |
| WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models |
| LLM-AutoDA: Large Language Model-Driven Automatic Data Augmentation for Long-tailed Problems |
| Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs |
| AGILE: A Novel Framework of LLM Agent |
| ALPINE: Unveiling The Planning Capability of Autoregressive Learning in Language Models |
| GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing |
| Web-Scale Visual Entity Recognition: An LLM-Driven Data Approach |
| Large Scale Transfer Learning for Tabular Data via Language Modeling |
| Stepwise Alignment for Constrained Language Model Policy Optimization |
| End-to-End Ontology Learning with Large Language Models |
| WizardArena: Post-training Large Language Models via Simulated Offline Chatbot Arena |
| Ad Auctions for LLMs via Retrieval Augmented Generation |
| LLaMo: Large Language Model-based Molecular Graph Assistant |
| D-LLM: A Token Adaptive Computing Resource Allocation Strategy for Large Language Models |
| LLM-based Skill Diffusion for Zero-shot Policy Adaptation |
| SGLang: Efficient Execution of Structured Language Model Programs |
| NoiseGPT: Label Noise Detection and Rectification through Probability Curvature |
| RaVL: Discovering and Mitigating Spurious Correlations in Fine-Tuned Vision-Language Models |
| Pretrained Large Language Models Use Fourier Features to Compute Addition |
| WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models |
| How Do Large Language Models Acquire Factual Knowledge During Pretraining? |
| Meaningful Learning: Enhancing Abstract Reasoning in Large Language Models via Generic Fact Guidance |
| Lever LM: Configuring In-Context Sequence to Lever Large Vision Language Models |
| GraphVis: Boosting LLMs with Visual Knowledge Graph Integration |
| CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts |
| HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models |
| Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models |
| BonBon Alignment for Large Language Models: on the Sweetness of Best-of-n Sampling |
| Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Models |
| Vision-Language Models are Strong Noisy Label Detectors |
| Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models |
| Online Adaptation of Language Models with a Memory of Amortized Contexts |
| FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptations |
| Information Re-Organization Improves Reasoning in Large Language Models |
| Large Language Models Must Be Taught to Know What They Don’t Know |
| Alleviating Hallucinations in Large Vision-Language Models through Hallucination-Induced Optimization |
| MoGU: A Framework for Enhancing Safety of Open-Sourced LLMs While Preserving Their Usability |
| The AlCHEmist: Automated Labeling 500x CHEaper than LLM Data Annotators |
| Unveiling Encoder-Free Vision-Language Models |
| Déjà Vu Memorization in Vision–Language Models |
| Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning |
| LLMDFA: Analyzing Dataflow in Code with Large Language Models |
| Mixture of In-Context Experts Enhance LLMs' Long Context Awareness |
| Leveraging Environment Interaction for Automated PDDL Generation and Planning with Large Language Models |
| Learning Goal-Conditioned Representations in Reward Models for Aligning Language Models |
| Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models |
| Tree of Attacks: Jailbreaking Black-Box LLMs Automatically |
| SpeechAlign: Speech Language Models Can Self-Improve via Preference Optimization |
| LACIE: Listener-Aware Finetuning for Calibration in Large Language Models |
| RankRAG: Unifying Retrieval-Augmented Generation and Context Ranking in LLMs |
| Deep Bayesian Active Learning for Preference Modeling in Large Language Models |
| Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters |
| ConStat: Performance-Based Contamination Detection in Large Language Models |
| Human-Readable Fingerprint for Large Language Models |
| Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning |
| MQT-LLaVA: Matryoshka Query Transformer for Large Vision-Language Models |
| Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search |
| Compact Language Models via Pruning and Knowledge Distillation |
| Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models |
| Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization |
| Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy |
| Implicit Multimodal Alignment: On the Generalization of Frozen LLMs to Multimodal Inputs |
| ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search |
| Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data |
| CogVLM: Visual Expert for Pretrained Language Models |
| EAI: Emotional Decision-Making of LLMs in Strategic Games and Ethical Dilemmas |
| Ensemble Learning for Heterogeneous Large Language Models with Deep Parallel Collaboration |
| Exploring the Role of Large Language Models in Prompt Encoding for Diffusion Models |
| Large Language Model Unlearning |
| Efficient Adversarial Training in LLMs with Continuous Attacks |
| When and How Does Synthetic Data Improve Reasoning Capabilities of Language Models? |
| Improved Generation of Adversarial Examples Against Safety-aligned LLMs |
| Slot-VLM: Object-Event Slots for Video-Language Modeling |
| Block Transformer: Global-to-Local Language Modeling for Fast Inference |
| PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models |
| Inevitable Trade-off between Watermark Strength and Speculative Sampling Efficiency for Language Models |
| HYSYNTH: Context-Free LLM Approximation for Guiding Program Synthesis |
| Stratified Prediction-Powered Inference for Effective Hybrid Evaluation of Language Models |
| HENASY: Learning to Assemble Scene-Entities for Interpretable Egocentric Video-Language Model |
| Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models |
| Prediction-Powered Ranking of Large Language Models |
| Adversarial Moment-Matching Distillation of Large Language Models |
| How does Architecture Influence the Base Capabilities of Pre-trained Language Models? A Case Study Based on FFN-Wider and MoE Transformers |
| RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models |
| MixEval: Fast and Dynamic Human Preference Approximation with LLM Benchmark Mixtures |
| Calibrated Preference Optimization for Direct Language Model Alignment |