Papers

New on arXiv

Fri 4 Oct 2024

376 papers

Depth-Guided Self-Supervised Human Keypoint Detection via Cross-Modal DistillationKnowledge distillation → Detection and dense prediction distillation
Knowledge-Augmented Reasoning for EUAIA Compliance and Adversarial Robustness of LLMsLLM reasoning → Reasoning for agents, planning and code
A Large Language Model-based Framework for Semi-Structured Tender Document Retrieval-Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
A Dynamic Approach to Stock Price Prediction: Comparing RNN and Mixture of Experts Models Across Different Volatility ProfilesMixture-of-experts → MoE for time series and graphs
ShieldDiff: Suppressing Sexual Content Generation from Diffusion Models through Reinforcement LearningDiffusion models → Robustness, privacy and adversarial aspects
Output Scouting: Auditing Large Language Models for Catastrophic ResponsesLLM safety and security → Safety alignment, refusal and guardrails
Developing Assurance Cases for Adversarial Robustness and Regulatory Compliance in LLMsLLM safety and security → Jailbreaking
SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model TransformationEfficient LLM inference and serving → KV cache optimization
AutoLoRA: AutoGuidance Meets Low-Rank Adaptation for Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
Online Posterior Sampling with a Diffusion PriorDiffusion models → Diffusion and flow policies for robotics
ActPlan-1K: Benchmarking the Procedural Planning Ability of Visual Language Models in Household ActivitiesLLM reasoning → Spatial and embodied reasoning +1
Chain-of-Jailbreak Attack for Image Generation Models via Editing Step by StepLLM safety and security → Vision-language and text-to-image safety
Can Language Models Reason about Individualistic Human Values and Preferences?LLM reasoning → Reasoning benchmarks and evaluation +1
DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories SearchLLM reasoning → Reasoning benchmarks and evaluation
MDMP: Multi-modal Diffusion for supervised Motion Predictions with uncertaintyDiffusion models → Video generation
You Know What I'm Saying: Jailbreak Attack via Implicit ReferenceLLM safety and security → Jailbreaking
Enhancing Inverse Reinforcement Learning through Encoding Dynamic Information in Reward ShapingOffline RL and imitation learning from data → Inverse reinforcement learning
Understanding Fine-tuning in Approximate Unlearning: A Theoretical PerspectiveLLM safety and security → Machine unlearning
Large Language Models can be Strong Self-DetoxifiersLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
Exploring the Limitations of Mamba in COPY and CoT ReasoningLLM reasoning → Test-time compute and efficient thinking +1
Mixture of Attentions For Speculative DecodingEfficient LLM inference and serving → Speculative decoding
Text-guided Diffusion Model for 3D Molecule GenerationDiffusion models → Flow matching, time series and science
Learning from Committee: Reasoning Distillation from a Mixture of Teachers with Peer-ReviewLLM reasoning → Prompting and chain-of-thought reasoning +1
System 2 Reasoning Capabilities Are NighLLM reasoning → Reasoning benchmarks and evaluation
Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
GenSim2: Scaling Robot Data Generation with Multi-modal and Reasoning LLMsWorld models → Embodied and robot world models +1
Aligning LLMs with Individual Preferences via InteractionLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
Real-World Benchmarks Make Membership Inference Attacks Fail on Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
Robust Offline Imitation Learning from Diverse Auxiliary DataOffline RL and imitation learning from data → Imitation learning methods
Open-World Reinforcement Learning over Long Short-Term ImaginationWorld models → Latent dynamics models and model-based RL +1
How Discrete and Continuous Diffusion Meet: Comprehensive Analysis of Discrete Diffusion Models via a Stochastic Integral FrameworkDiffusion models → Diffusion foundations and sampling
Efficiently Identifying Watermarked Segments in Mixed-Source TextsLLM safety and security → Watermarking generated content and models
Understanding Reasoning in Chain-of-Thought from the Hopfieldian ViewLLM reasoning → Prompting and chain-of-thought reasoning
Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
FAERDXEL: An Expert System for Danish Traffic LawLLM reasoning → Reasoning for agents, planning and code
Not All Diffusion Model Activations Have Been Evaluated as Discriminative FeaturesDiffusion models → Image generation, text-to-image and editing
Ward: Provable RAG Dataset Inference via LLM WatermarksLLM safety and security → Membership inference attacks
Steering Large Language Models between Code Execution and Textual ReasoningLLM reasoning → Reasoning for agents, planning and code
A Probabilistic Perspective on Unlearning and Alignment for Large Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods +1
HMT-Grasp: A Hybrid Mamba-Transformer Approach for Robot Grasping in Cluttered EnvironmentsState-space sequence models (S4, Mamba) → Vision Mamba backbones
Gradient-based Jailbreak Images for Multimodal Fusion ModelsLLM safety and security → Vision-language and text-to-image safety
STREAMS: An Assistive Multimodal AI Framework for Empowering Biosignal Based Robotic ControlsDeep reinforcement learning methods → RL for robot locomotion and manipulation
Is Safer Better? The Impact of Guardrails on the Argumentative Strength of LLMs in Hate Speech CounteringLLM safety and security → Safety alignment, refusal and guardrails
Diffusion State-Guided Projected Gradient for Inverse ProblemsDiffusion models → Inverse problems and image restoration
Auto-GDA: Automatic Domain Adaptation for Efficient Grounding Verification in Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
Dynamic Diffusion TransformerDiffusion models → Diffusion foundations and sampling
MLLM as Retriever: Interactively Learning Multimodal Retrieval for Embodied AgentsLLM agents and tool use → Multimodal and embodied agents
CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character controlDiffusion models → Diffusion and flow policies for robotics +1
Exploring the Benefit of Activation Sparsity in Pre-trainingMixture-of-experts → MoE theory and gating functions
Predictive Coding for Decision TransformerOffline RL and imitation learning from data → Decision transformers and sequence modeling
Mitigating Adversarial Perturbations for Deep Reinforcement Learning via Vector QuantizationDeep reinforcement learning methods → Adversarial robustness and RL in finance
Latent Abstractions in Generative Diffusion ModelsDiffusion models → Diffusion foundations and sampling
LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative DecodingDiffusion models → Image generation, text-to-image and editing +1
Dolphin: A Programmable Framework for Scalable Neurosymbolic LearningLLM reasoning → Reasoning benchmarks and evaluation
Audio-Agent: Leveraging LLMs For Audio Generation, Editing and CompositionLLM agents and tool use → Multimodal and embodied agents
An X-Ray Is Worth 15 Features: Sparse Autoencoders for Interpretable Radiology Report GenerationMechanistic interpretability → Interpreting biomedical and science models
Visual-O1: Understanding Ambiguous Instructions via Multi-modal Multi-turn Chain-of-thoughts ReasoningLLM reasoning → Multimodal reasoning
SELU: Self-Learning Embodied MLLMs in Unknown EnvironmentsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Demystifying the Token Dynamics of Deep Selective State Space ModelsState-space sequence models (S4, Mamba) → Core SSM architectures for language
Latent Action Priors for Locomotion with Deep Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
Elucidating the Design Choice of Probability Paths in Flow Matching for ForecastingDiffusion models → Flow matching, time series and science
ALR2: A Retrieve-then-Reason Framework for Long-context Question AnsweringLLM reasoning → Reasoning benchmarks and evaluation
AutoPenBench: Benchmarking Generative Agents for Penetration TestingLLM agents and tool use → Agent threats, guardrails and governance
Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample OptimizationDiffusion models → Diffusion foundations and sampling
Generalizable Prompt Tuning for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Kiss up, Kick down: Exploring Behavioral Changes in Multi-modal Large Language Models with Assigned Visual PersonasMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Investigating and Mitigating Object Hallucinations in Pretrained Vision-Language (CLIP) ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
Can Watermarked LLMs be Identified by Users via Crafted Prompts?LLM safety and security → Watermarking generated content and models
Adaptive Masking Enhances Visual GroundingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep ApproachDiffusion models → Video generation
Mathematical Formalism for Memory Compression in Selective State Space ModelsState-space sequence models (S4, Mamba) → Core SSM architectures for language
Margin Matching Preference Optimization: Enhanced Model Alignment with Granular FeedbackLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Deliberate Reasoning in Language Models as Structure-Aware Planning with an Accurate World ModelWorld models → World models for language agents +1
RIPPLECOT: Amplifying Ripple Effect of Knowledge Editing in Language Models via Chain-of-Thought In-Context LearningLLM reasoning → Knowledge- and tool-augmented reasoning
Spatial-Aware Decision-Making with Ring Attractors in Reinforcement Learning SystemsDeep reinforcement learning methods → Deep RL algorithms and representations
ProcBench: Benchmark for Multi-Step Reasoning and Following ProcedureLLM reasoning → Reasoning benchmarks and evaluation
LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression StrategyEfficient LLM inference and serving → KV cache optimization
A Training-Free Conditional Diffusion Model for Learning Stochastic Dynamical SystemsDiffusion models → Diffusion foundations and sampling
A Policy Iteration Algorithm for N-player General-Sum Linear Quadratic Dynamic GamesDeep reinforcement learning methods → RL for games and combinatorial optimization
Mamba in Vision: A Comprehensive Survey of Techniques and ApplicationsState-space sequence models (S4, Mamba) → Vision Mamba backbones
UNComp: Can Matrix Entropy Uncover Sparsity? -- A Compressor Design from an Uncertainty-Aware PerspectiveEfficient LLM inference and serving → KV cache optimization
Generative Edge Detection with Stable DiffusionDiffusion models → Diffusion foundations and sampling
Residual Policy Learning for Perceptive Quadruped Control Using Differentiable SimulationDeep reinforcement learning methods → RL for robot locomotion and manipulation
Multi-Robot Motion Planning with Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics
Compute Or Load KV Cache? Why Not Both?Efficient LLM inference and serving → KV cache optimization
Image First or Text First? Optimising the Sequencing of Modalities in Large Language Model Prompting and Reasoning TasksLLM reasoning → Multimodal reasoning
DocKD: Knowledge Distillation from LLMs for Open-World Document Understanding ModelsKnowledge distillation → Knowledge distillation for LLMs
CLIP-Clique: Graph-based Correspondence Matching Augmented by Vision Language Models for Object-based Global LocalizationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
The Effect of Acute Stress on the Interpretability and Generalization of Schizophrenia Predictive Machine Learning Models
Inference with K-means
Optimal Ground Station Selection for Low-Earth Orbiting Satellites
Verification of Neural Control Barrier Functions with Symbolic Derivative Bounds Propagation
Deep Learning Enhanced Road Traffic Analysis: Scalable Vehicle Detection and Velocity Estimation Using PlanetScope Imagery
Learning Cortico-Muscular Dependence through Orthonormal Decomposition of Density Ratios
REBIND: Enhancing ground-state molecular conformation via force-based graph rewiring
Deep Domain Isolation and Sample Clustered Federated Learning for Semantic Segmentation
Green vehicle routing problem that jointly optimizes delivery speed and routing based on the characteristics of electric vehicles
LLMBridge: Reducing Costs to Access LLMs in a Prompt-Centric Internet
Crafting Narrative Closures: Zero-Shot Learning with SSM Mamba for Short Story Ending Generation
Leveraging Social Determinants of Health in Alzheimer's Research Using LLM-Augmented Literature Mining and Knowledge Graphs

All 376