Papers

New on arXiv

Thu 12 Dec 2024

368 papers

Dipper: Diversity in Prompts for Producing Large Language Model Ensembles in Reasoning tasksLLM reasoning → Reasoning benchmarks and evaluation
OG-RAG: Ontology-Grounded Retrieval-Augmented Generation For Large Language ModelsRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
Explore Theory of Mind: Program-guided adversarial data generation for theory of mind reasoningLLM reasoning → Reasoning benchmarks and evaluation
A NotSo Simple Way to Beat Simple BenchLLM reasoning → Reasoning benchmarks and evaluation
VCA: Video Curious Agent for Long Video UnderstandingLLM agents and tool use → Multimodal and embodied agents
Geo-LLaVA: A Large Multi-Modal Model for Solving Geometry Math Problems with Meta In-Context LearningLLM reasoning → Spatial and embodied reasoning +1
ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded SegmentationMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
The Unreasonable Effectiveness of Gaussian Score Approximation for Diffusion Models and its ApplicationsDiffusion models → Diffusion foundations and sampling
GReaTer: Gradients over Reasoning Makes Smaller Language Models Strong Prompt OptimizersLLM reasoning → Prompting and chain-of-thought reasoning
BayesAdapter: enhanced uncertainty estimation in CLIP few-shot adaptationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Vision-Language Models Generate More Homogeneous Stories for Phenotypically Black IndividualsMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
From Noise to Nuance: Advances in Deep Generative Image ModelsDiffusion models → Diffusion foundations and sampling
Doe-1: Closed-Loop Autonomous Driving with Large World ModelWorld models → World models for autonomous driving +1
FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale FusionDiffusion models → Diffusion foundations and sampling
Illusion3D: 3D Multiview Illusion with 2D Diffusion PriorsDiffusion models → 3D, point cloud and scene generation
LoRACLR: Contrastive Adaptation for Customization of Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and TrainingDiffusion models → Image generation, text-to-image and editing +1
EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLMMultimodal LLMs / vision-language models → Image editing and quality assessment +1
V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position EncodingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
RAVEL: Rare Concept Generation and Editing via Graph-driven Relational GuidanceDiffusion models → Image generation, text-to-image and editing
PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
Olympus: A Universal Task Router for Computer Vision TasksMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
FluxSpace: Disentangled Semantic Editing in Rectified Flow TransformersDiffusion models → Image generation, text-to-image and editing
AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web TutorialsLLM agents and tool use → Web, search, and research agents
Do MLLMs Exhibit Human-like Perceptual Behaviors? HVSBench: A Benchmark for MLLM Alignment with Human Perceptual BehaviorMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
Hidden Biases of End-to-End Driving DatasetsEnd-to-end autonomous driving → End-to-end system architecture
Owl-1: Omni World Model for Consistent Long Video GenerationWorld models → Video-generation world models and simulators
InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio InteractionsMultimodal LLMs / vision-language models → Video understanding with MLLMs
Neural LightRig: Unlocking Accurate Object Normal and Material Estimation with Multi-Light DiffusionDiffusion models → 3D, point cloud and scene generation
Elevating Visual Perception in Multimodal LLMs with Visual Embedding DistillationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
A Theoretical Analysis of Soft-Label vs Hard-Label Training in Neural NetworksKnowledge distillation → General knowledge distillation methods
Rethinking LLM Uncertainty: A Multi-Agent Approach to Estimating Black-Box Model UncertaintyLLM reasoning → Hallucination detection and mitigation +1
SimAvatar: Simulation-Ready Avatars with Layered Hair and ClothingDiffusion models → 3D, point cloud and scene generation
Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward HackingLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
Dynamic-VLM: Simple Dynamic Visual Token Compression for VideoLLMMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
How Well Can Modern LLMs Act as Agent Cores in Radiology Environments?LLM agents and tool use → Medical and scientific domain agents
Efficient and Comprehensive Feature Extraction in Large Vision-Language Model for Pathology AnalysisMultimodal LLMs / vision-language models → Medical vision-language models
GainAdaptor: Learning Quadrupedal Locomotion with Dual Actors for Adaptable and Energy-Efficient Walking on Various TerrainsDeep reinforcement learning methods → RL for robot locomotion and manipulation
Lyra: An Efficient and Speech-Centric Framework for Omni-CognitionMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Distributional Reinforcement Learning based Integrated Decision Making and Control for Autonomous Surface VehiclesDeep reinforcement learning methods → RL for robot navigation and UAV control
Reinforcement Learning Within the Classical Robotics Stack: A Case Study in Robot SoccerDeep reinforcement learning methods → RL for robot locomotion and manipulation
Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning SystemsLLM reasoning → Test-time compute and efficient thinking
UFO: Enhancing Diffusion-Based Video Generation with a Uniform Frame OrganizerDiffusion models → Video generation
All You Need in Knowledge Distillation Is a Tailored Coordinate SystemKnowledge distillation → General knowledge distillation methods
AI Predicts AGI: Leveraging AGI Forecasting and Peer Review to Explore LLMs' Complex Reasoning CapabilitiesLLM reasoning → Reasoning benchmarks and evaluation
Diffusion Model with Representation Alignment for Protein Inverse FoldingDiffusion models → Flow matching, time series and science
Causal Graphical Models for Vision-Language Compositional UnderstandingMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Diffusion Predictive Control with ConstraintsDiffusion models → Diffusion and flow policies for robotics
Auto-Regressive Moving Diffusion Models for Time Series ForecastingDiffusion models → Flow matching, time series and science
Are Conditional Latent Diffusion Models Effective for Image Restoration?Diffusion models → Inverse problems and image restoration
Coarse Q-learning: Indifference, Indeterminacy, and InstabilityDeep reinforcement learning methods → RL theory and sample complexity
Optimising TinyML with Quantization and Distillation of Transformer and Mamba Models for Indoor Localisation on Edge DevicesState-space sequence models (S4, Mamba) → Core SSM architectures for language
Towards a Multimodal Large Language Model with Pixel-Level Insight for BiomedicineMultimodal LLMs / vision-language models → Medical vision-language models +1
LatentSync: Taming Audio-Conditioned Latent Diffusion Models for Lip Sync with SyncNet SupervisionDiffusion models → Audio, speech and music
SPRec: Self-Play to Debias LLM-based RecommendationSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
LMAgent: A Large-scale Multimodal Agents Society for Multi-user SimulationLLM agents and tool use → General LLM agent frameworks and benchmarks
DASK: Distribution Rehearsing via Adaptive Style Kernel Learning for Exemplar-Free Lifelong Person Re-IdentificationKnowledge distillation → Distillation for continual learning
ExpRDiff: Short-exposure Guided Diffusion Model for Realistic Local Motion DeblurringDiffusion models → Inverse problems and image restoration
RAD: Region-Aware Diffusion Models for Image InpaintingDiffusion models → 3D, point cloud and scene generation
Student-Informed Teacher TrainingOffline RL and imitation learning from data → Imitation learning methods +1
LVMark: Robust Watermark for Latent Video Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
The Utility and Complexity of in- and out-of-Distribution Machine UnlearningLLM safety and security → Machine unlearning
In-Dataset Trajectory Return Regularization for Offline Preference-based Reinforcement LearningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM ReasoningLLM reasoning → Test-time compute and efficient thinking
DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous DrivingWorld models → World models for autonomous driving
ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer UncertaintyEfficient LLM inference and serving → KV cache optimization
Video Anomaly Detection with Motion and Appearance Guided Patch Diffusion ModelDiffusion models → Flow matching, time series and science
Arbitrary-steps Image Super-resolution via Diffusion InversionDiffusion models → Inverse problems and image restoration
KnowShiftQA: How Robust are RAG Systems when Textbook Knowledge Shifts in K-12 Education?Retrieval-augmented generation → RAG robustness and adaptive retrieval
A Wander Through the Multimodal Landscape: Efficient Transfer Learning via Low-rank Sequence Multimodal AdapterMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World ScenariosLLM reasoning → Reasoning benchmarks and evaluation
Reasoning-Aware Query-Focused Summarization over Multi-Table DataLLM reasoning → Knowledge- and tool-augmented reasoning
Deep Learning Model Security: Threats and DefensesLLM safety and security → Backdoor and data poisoning attacks
Tuned Reverse Distillation: Enhancing Multimodal Industrial Anomaly Detection with Crossmodal TunersKnowledge distillation → Detection and dense prediction distillation
Mojito: Motion Trajectory and Intensity Control for Video GenerationDiffusion models → Video generation
Selective Visual Prompting in Vision MambaState-space sequence models (S4, Mamba) → Vision Mamba backbones
MoSLD: An Extremely Parameter-Efficient Mixture-of-Shared LoRAs for Multi-Task LearningMixture-of-experts → Mixture of LoRA experts
Dynamic Contrastive Knowledge Distillation for Efficient Image RestorationKnowledge distillation → General knowledge distillation methods
From Text to Trajectory: Exploring Complex Constraint Representation and Decomposition in Safe Reinforcement LearningDeep reinforcement learning methods → Safe and constrained RL
Reversing the Damage: A QP-Aware Transformer-Diffusion Approach for 8K Video Restoration under Codec CompressionDiffusion models → Inverse problems and image restoration
Optimal Control with Natural Images: Efficient Reinforcement Learning using Overcomplete Sparse CodesDeep reinforcement learning methods → Deep RL algorithms and representations
Lexico: Extreme KV Cache Compression via Sparse Coding over Universal DictionariesEfficient LLM inference and serving → KV cache optimization
FAWAC: Feasibility Informed Advantage Weighted Regression for Persistent Safety in Offline Reinforcement LearningOffline RL and imitation learning from data → Safe offline RL
Inference-Time Diffusion Model DistillationDiffusion models → Diffusion foundations and sampling
GRIP: A Graph-Based Reasoning Instruction ProducerLLM reasoning → Knowledge- and tool-augmented reasoning
Complex-Cycle-Consistent Diffusion Model for Monaural Speech EnhancementDiffusion models → Audio, speech and music
On Design Choices in Similarity-Preserving Sparse Randomized Embeddings
Reproduction Research of FSA-Benchmark
Creative Loss: Ambiguity, Uncertainty and Indeterminacy
The Potential of Answer Classes in Large-scale Written Computer-Science Exams -- Vol. 2
GTDE: Grouped Training with Decentralized Execution for Multi-agent Actor-Critic
Neural networks consisting of DNA
CareBot: A Pioneering Full-Process Open-Source Medical Language Model
Feasibility of Detecting Cognitive Impairment and Psychological Well-being among Older Adults Using Facial, Acoustic, Linguistic, and Cardiovascular Patterns Derived from Remote Conversations
Whom do Explanations Serve? A Systematic Literature Survey of User Characteristics in Explainable Recommender Systems Evaluation
An introduction to reservoir computing
AI Adoption to Combat Financial Crime: Study on Natural Language Processing in Adverse Media Screening of Financial Services in English and Bangla multilingual interpretation
PickLLM: Context-Aware RL-Assisted Large Language Model Routing
Regulation of Language Models With Interpretability Will Likely Result In A Performance Trade-Off
A Decomposition Modeling Framework for Seasonal Time-Series Forecasting

All 368