Papers

New on arXiv

Tue 15 Oct 2024

396 papers

Unsupervised Training of Diffusion Models for Feasible Solution Generation in Neural Combinatorial OptimizationDiffusion models → Diffusion foundations and sampling
Exploiting Risk-Aversion and Size-dependent fees in FX Trading with Fitted Natural Actor-CriticDeep reinforcement learning methods → Adversarial robustness and RL in finance
RuleRAG: Rule-Guided Retrieval-Augmented Generation with Language Models for Question AnsweringRetrieval-augmented generation → RAG robustness and adaptive retrieval
Advancements in Visual Language Models for Remote Sensing: Datasets, Capabilities, and Enhancement TechniquesMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
A Formal Framework for Assessing and Mitigating Emergent Security Risks in Generative AI Models: Bridging Theory and Dynamic Risk MitigationDiffusion models → Robustness, privacy and adversarial aspects
MIND: Math Informed syNthetic Dialogues for Pretraining LLMsLLM reasoning → Mathematical reasoning
Improving Instruction-Following in Language Models through Activation SteeringMechanistic interpretability → Activation steering methods
In-context KV-Cache Eviction for LLMs via Attention-GateEfficient LLM inference and serving → KV cache optimization
Learning from 10 Demos: Generalisable and Sample-Efficient Policy Learning with Oriented Affordance FramesOffline RL and imitation learning from data → Robot manipulation imitation learning
Large Language Models, and LLM-Based Agents, Should Be Used to Enhance the Digital Public SphereLLM agents and tool use → Agentic recommender systems
OMCAT: Omni Context Aware TransformerMultimodal LLMs / vision-language models → Video understanding with MLLMs
The Persian Rug: solving toy models of superposition using large-scale symmetriesMechanistic interpretability → Sparse autoencoder training and evaluation
WeatherDG: LLM-assisted Diffusion Model for Procedural Weather Generation in Domain-Generalized Semantic SegmentationDiffusion models → Medical imaging and segmentation
De-jargonizing Science for Journalists with GPT-4: A Pilot StudyRetrieval-augmented generation → Agentic RAG, agents and memory
MFC-EQ: Mean-Field Control with Envelope Q-Learning for Moving Decentralized Agents in FormationDeep reinforcement learning methods → RL for games and combinatorial optimization
Boosting Logical Fallacy Reasoning in LLMs via Logical Structure TreeLLM reasoning → Reasoning benchmarks and evaluation
Concept-Reversed Winograd Schema Challenge: Evaluating and Improving Robust Reasoning in Large Language Models via AbstractionLLM reasoning → Reasoning benchmarks and evaluation
MoE-Pruner: Pruning Mixture-of-Experts Large Language Model using the Hints from Its RouterMixture-of-experts → MoE large language models +1
Toolken+: Improving LLM Tool Usage with Reranking and a Reject OptionLLM agents and tool use → Tool learning and function calling
Holistic Reasoning with Long-Context LMs: A Benchmark for Database Operations on Massive Textual DataLLM reasoning → Knowledge- and tool-augmented reasoning +1
DDIL: Diversity Enhancing Diffusion Distillation With Imitation LearningDiffusion models → Diffusion foundations and sampling +1
Physical Informed-Inspired Deep Reinforcement Learning Based Bi-Level Programming for Microgrid SchedulingDeep reinforcement learning methods → RL for energy, networks and operations
Empowering Users in Digital Privacy Management through Interactive LLM-Based AgentsLLM agents and tool use → Agent threats, guardrails and governance
MoH: Multi-Head Attention as Mixture-of-Head AttentionMixture-of-experts → Expert routing strategies
GaVaMoE: Gaussian-Variational Gated Mixture of Experts for Explainable RecommendationMixture-of-experts → MoE for recommender systems
High-Resolution Frame Interpolation with Patch-based Cascaded DiffusionDiffusion models → Diffusion foundations and sampling
Aligned Datasets Improve Detection of Latent Diffusion-Generated ImagesDiffusion models → Image generation, text-to-image and editing
Mitigating Suboptimality of Deterministic Policy Gradients in Complex Q-functionsDeep reinforcement learning methods → RL theory and sample complexity
MMFuser: Multimodal Multi-Layer Feature Fuser for Fine-Grained Vision-Language UnderstandingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Learning Smooth Humanoid Locomotion through Lipschitz-Constrained PoliciesDeep reinforcement learning methods → RL for robot locomotion and manipulation
KITTEN: A Knowledge-Intensive Evaluation of Image Generation on Visual EntitiesRetrieval-augmented generation → Multimodal RAG
Improving Long-Text Alignment for Text-to-Image Diffusion ModelsDiffusion models → Image generation, text-to-image and editing +1
NesTools: A Dataset for Evaluating Nested Tool Learning Abilities of Large Language ModelsLLM agents and tool use → Tool learning and function calling
Efficient Diffusion Models: A Comprehensive Survey from Principles to PracticesDiffusion models → Diffusion foundations and sampling
Solving The Dynamic Volatility Fitting Problem: A Deep Reinforcement Learning ApproachDeep reinforcement learning methods → Adversarial robustness and RL in finance
Selection-p: Self-Supervised Task-Agnostic Prompt Compression for Faithfulness and TransferabilityEfficient LLM inference and serving → Prompt and context compression
G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural NetworksLLM agents and tool use → General LLM agent frameworks and benchmarks
MLLM can see? Dynamic Correction Decoding for Hallucination MitigationMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
Analyzing (In)Abilities of SAEs via Formal LanguagesMechanistic interpretability → Sparse autoencoder training and evaluation
SlideChat: A Large Vision-Language Assistant for Whole-Slide Pathology Image UnderstandingMultimodal LLMs / vision-language models → Medical vision-language models
Latent Action Pretraining from VideosVision-language-action models → Human-video and latent-action pretraining
DySpec: Faster Speculative Decoding with Dynamic Token Tree StructureEfficient LLM inference and serving → Speculative decoding
Patch-Based Diffusion Models Beat Whole-Image Models for Mismatched Distribution Inverse ProblemsDiffusion models → Inverse problems and image restoration
Magnifier Prompt: Tackling Multimodal Hallucination via Extremely Simple InstructionsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
BlendRL: A Framework for Merging Symbolic and Neural Policy LearningLLM reasoning → Reinforcement learning for reasoning
A Survey of Low-shot Vision-Language Model Adaptation via Representer TheoremMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Understanding Likelihood Over-optimisation in Direct Alignment AlgorithmsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Safety Filtering While Training: Improving the Performance and Sample Efficiency of Reinforcement Learning AgentsDeep reinforcement learning methods → Safe and constrained RL
VisualRWKV-HD and UHD: Advancing High-Resolution Processing for Visual Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Retrieval Augmented Spelling Correction for E-Commerce ApplicationsRetrieval-augmented generation → RAG pipeline design and evaluation
Transformer Layer Injection: A Novel Approach for Efficient Upscaling of Large Language ModelsMixture-of-experts → MoE large language models
Improve Value Estimation of Q Function and Reshape Reward with Monte Carlo Tree SearchDeep reinforcement learning methods → RL for games and combinatorial optimization
Efficient and Effective Universal Adversarial Attack against Vision-Language Pre-training ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
Simultaneous Diffusion Sampling for Conditional LiDAR GenerationWorld models → World modeling from LiDAR generation +1
VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AILLM reasoning → Spatial and embodied reasoning +1
Causal Reasoning in Large Language Models: A Knowledge Graph ApproachLLM reasoning → Knowledge- and tool-augmented reasoning
Breaking Modality Gap in RGBT Tracking: Coupled Knowledge DistillationKnowledge distillation → Detection and dense prediction distillation
DeformPAM: Data-Efficient Learning for Long-horizon Deformable Object Manipulation via Preference-based Action AlignmentLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
PAVLM: Advancing Point Cloud based Affordance Understanding Via Vision-Language ModelMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
MCTBench: Multimodal Cognition towards Text-Rich Visual Scenes BenchmarkMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Multi-round jailbreak attack on large language modelsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
AGENTiGraph: An Interactive Knowledge Graph Platform for LLM-based Chatbots Utilizing Private DataLLM reasoning → Knowledge- and tool-augmented reasoning
It Takes Two to Tango: Directly Optimizing for Constrained Synthesizability in Generative Molecular DesignDeep reinforcement learning methods → RL for energy, networks and operations
Rician Denoising Diffusion Probabilistic Models For Sodium Breast MRI EnhancementDiffusion models → Medical imaging and segmentation
Dual-Teacher Ensemble Models with Double-Copy-Paste for 3D Semi-Supervised Medical Image SegmentationKnowledge distillation → Distillation for medical imaging
DynamicER: Resolving Emerging Mentions to Dynamic Entities for RAGRetrieval-augmented generation → RAG pipeline design and evaluation
InvSeg: Test-Time Prompt Inversion for Semantic SegmentationDiffusion models → Medical imaging and segmentation
Can sparse autoencoders make sense of gene expression latent variable models?Mechanistic interpretability → Interpreting biomedical and science models
Advanced Persistent Threats (APT) Attribution Using Deep Reinforcement LearningDeep reinforcement learning methods → Adversarial robustness and RL in finance
Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language ModelsLLM reasoning → Reasoning for agents, planning and code +1
Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model DisentanglementWorld models → Latent dynamics models and model-based RL
AIC CTU system at AVeriTeC: Re-framing automated fact-checking as a simple RAG taskRetrieval-augmented generation → RAG robustness and adaptive retrieval
Difficult Task Yes but Simple Task No: Unveiling the Laziness in Multimodal LLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Hessian-Informed Flow MatchingDiffusion models → Flow matching, time series and science
VidCompress: Memory-Enhanced Temporal Compression for Video Understanding in Large Language ModelsMultimodal LLMs / vision-language models → Video understanding with MLLMs
ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic InterpretabilityRetrieval-augmented generation → Hallucination detection in RAG +1
PMMT: Preference Alignment in Multilingual Machine Translation via LLM DistillationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
M2Diffuser: Diffusion-based Trajectory Optimization for Mobile Manipulation in 3D ScenesDiffusion models → Diffusion and flow policies for robotics
LLM2Swarm: Robot Swarms that Responsively Reason, Plan, and Collaborate through LLMsLLM reasoning → Spatial and embodied reasoning
Learning from Imperfect Data: Towards Efficient Knowledge Distillation of Autoregressive Language Models for Text-to-SQLKnowledge distillation → Knowledge distillation for LLMs
Enhance Graph Alignment for Large Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
DODT: Enhanced Online Decision Transformer Learning through Dreamer's Actor-Critic Trajectory ForecastingOffline RL and imitation learning from data → Decision transformers and sequence modeling +1
RATE: Causal Explainability of Reward Models with Imperfect CounterfactualsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
DIAR: Diffusion-model-guided Implicit Q-learning with Adaptive RevaluationDiffusion models → Diffusion and flow policies for robotics +2
Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved SamplingKnowledge distillation → General knowledge distillation methods
Diffusion-Based Offline RL for Improved Decision-Making in Augmented ARC TaskOffline RL and imitation learning from data → Offline RL algorithms
Self-adaptive Multimodal Retrieval-Augmented GenerationRetrieval-augmented generation → Multimodal RAG
Deciphering the Chaos: Enhancing Jailbreak Attacks via Adversarial Prompt TranslationLLM safety and security → Jailbreaking
SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval +1
QSpec: Speculative Decoding with Complementary Quantization SchemesEfficient LLM inference and serving → Speculative decoding
Diff-SAGe: End-to-End Spatial Audio Generation Using Diffusion ModelsDiffusion models → Audio, speech and music
Process Reward Model with Q-Value RankingsLLM reasoning → Reinforcement learning for reasoning +1
AdvBDGen: Adversarially Fortified Prompt-Specific Fuzzy Backdoor Generator Against LLM AlignmentLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
Multi-Objective-Optimization Assisted Data Collection Framework for IoUT Based on Offline ReinforcementOffline RL and imitation learning from data → Offline RL algorithms
UmambaTSF: A U-shaped Multi-Scale Long-Term Time Series Forecasting Method Using MambaState-space sequence models (S4, Mamba) → Time series forecasting with SSMs
ILAEDA: An Imitation Learning Based Approach for Automatic Exploratory Data AnalysisOffline RL and imitation learning from data → Imitation learning methods +1
Shallow diffusion networks provably learn hidden low-dimensional structureDiffusion models → Diffusion foundations and sampling
Cognitive Overload Attack:Prompt Injection for Long ContextLLM safety and security → Jailbreaking
Unveiling Options with Neural DecompositionDeep reinforcement learning methods → Deep RL algorithms and representations
Disentangled Unsupervised Skill Discovery for Efficient Hierarchical Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations

All 396