Papers

New on arXiv

Sun 1 Dec 2024

152 papers

Provable Partially Observable Reinforcement Learning with Privileged InformationDeep reinforcement learning methods → RL theory and sample complexity
Hierarchical Prompt Decision Transformer: Improving Few-Shot Policy Generalization with Global and Adaptive GuidanceOffline RL and imitation learning from data → Decision transformers and sequence modeling +1
Generating AI Literacy MCQs: A Multi-Agent LLM ApproachLLM agents and tool use → Educational agents and math problem solving
Linear Probe Penalties Reduce LLM SycophancyLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
Token Cropr: Faster ViTs for Quite a Few TasksEfficient LLM inference and serving → Token pruning and merging for ViTs
STEVE-Audio: Expanding the Goal Conditioning Modalities of Embodied Agents in MinecraftLLM agents and tool use → Reinforcement learning for LLM agents
VisOnlyQA: Large Vision Language Models Still Struggle with Visual Perception of Geometric InformationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Bilinear Convolution Decomposition for Causal RL InterpretabilityDeep reinforcement learning methods → Interpretable and logic-guided RL
VISTA: Enhancing Long-Duration and High-Resolution Video Understanding by Video Spatiotemporal AugmentationMultimodal LLMs / vision-language models → Video understanding with MLLMs
Exploring Large Vision-Language Models for Robust and Efficient Industrial Anomaly DetectionMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
Learn to Unlearn: Meta-Learning-Based Knowledge Graph Embedding UnlearningLLM safety and security → Machine unlearning
Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context SparsificationMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
Improving Multimodal LLMs Ability In Geometry Problem Solving, Reasoning, And Multistep ScoringLLM reasoning → Spatial and embodied reasoning +1
Particle-based 6D Object Pose Estimation from Point Clouds using Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
AlignMamba: Enhancing Multimodal Mamba with Local and Global Cross-modal AlignmentState-space sequence models (S4, Mamba) → Vision Mamba backbones
EventGPT: Event Stream Understanding with Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Video understanding with MLLMs
Improving Physics Reasoning in Large Language Models Using Mixture of Refinement AgentsLLM reasoning → Spatial and embodied reasoning +1
Examining Identity Drift in Conversations of LLM AgentsLLM agents and tool use → Social simulation and multi-agent debate
Online Poisoning Attack Against Reinforcement Learning under Black-box EnvironmentsDeep reinforcement learning methods → Adversarial robustness and RL in finance
Memories of Forgotten ConceptsDiffusion models → Robustness, privacy and adversarial aspects
Learning Mamba as a Continual Learner: Meta-Learning Selective State Space Models for Continual LearningState-space sequence models (S4, Mamba) → Core SSM architectures for language
DIVD: Deblurring with Improved Video Diffusion ModelDiffusion models → Inverse problems and image restoration
SelfPrompt: Autonomously Evaluating LLM Robustness via Domain-Constrained Knowledge Guidelines and Refined Adversarial PromptsLLM safety and security → Safety alignment, refusal and guardrails
Learning to Forget using HypernetworksLLM safety and security → Machine unlearning
DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective SchedulingDiffusion models → Diffusion and flow policies for robotics +1
Open-World Drone Active Tracking with Goal-Centered RewardsDeep reinforcement learning methods → RL for robot navigation and UAV control
Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion TransformerDiffusion models → Audio, speech and music
Perturb and Recover: Fine-tuning for Effective Backdoor Removal from CLIPMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
Decision Transformer vs. Decision Mamba: Analysing the Complexity of Sequential Decision Making in Atari GamesOffline RL and imitation learning from data → Decision transformers and sequence modeling +1
LVLM-COUNT: Enhancing the Counting Ability of Large Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
2DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image ClassificationState-space sequence models (S4, Mamba) → Vision Mamba backbones
FiffDepth: Feed-forward Transformation of Diffusion-Based Generators for Detailed Depth EstimationDiffusion models → 3D, point cloud and scene generation
Learning on Less: Constraining Pre-trained Model Learning for Generalizable Diffusion-Generated Image DetectionDiffusion models → Image generation, text-to-image and editing
Improving Decoupled Posterior Sampling for Inverse Problems using Data Consistency ConstraintDiffusion models → Inverse problems and image restoration
Improving Vietnamese Legal Document Retrieval using Synthetic DataSynthetic data and self-improvement for LLMs → LLM synthetic data generation
Multi-Agent Collaboration in Incident Response with Large Language ModelsLLM agents and tool use → Agent threats, guardrails and governance
Sketch-Guided Stylized Landscape Cinemagraph SynthesisDiffusion models → Image generation, text-to-image and editing
MambaNUT: Nighttime UAV Tracking via Mamba-based Adaptive Curriculum LearningState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
VideoSAVi: Self-Aligned Video Language Models without Human SupervisionLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
A Lesson in Splats: Teacher-Guided Diffusion for 3D Gaussian Splats Generation with 2D SupervisionDiffusion models → 3D, point cloud and scene generation
Generative Modeling of Neural Dynamics via Latent Stochastic Differential Equations
Voice Biomarker Analysis and Automated Severity Classification of Dysarthric Speech in a Multilingual Context
Computational Methods for Breast Cancer Molecular Profiling through Routine Histopathology: A Review
Automatic answering of scientific questions using the FACTS-V1 framework: New methods in research to increase efficiency through the use of AI
LUIEO: A Lightweight Model for Integrating Underwater Image Enhancement and Object Detection
Text Is Not All You Need: Multimodal Prompting Helps LLMs Understand Humor
Large Language Models in Politics and Democracy: A Comprehensive Survey
Enhancing brain age estimation with structural MRI and synthesized cerebral blood volume maps
Learning Aggregation Rules in Participatory Budgeting: A Data-Driven Approach
Late fusion ensembles for speech recognition on diverse input audio representations
Pairwise Discernment of AffectNet Expressions with ArcFace
BAFPN: Bi directional alignment of features to improve localization accuracy
CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking
Take Only What You Need: Rank Minimization as an Implicit Forgetting Regularizer in Continual Learning
Competition Dynamics Shape Algorithmic Phases of In-Context Learning
PIAD-SRNN: Physics-Informed Adaptive Decomposition in State-Space RNN
TGTOD: A Global Temporal Graph Transformer for Outlier Detection at Scale
Incentivizing Truthful Collaboration in Heterogeneous Federated Learning
Optimal Algorithms for Augmented Testing of Discrete Distributions
From Priest to Doctor: Domain Adaptation for Low-Resource Neural Machine Translation
LLMs as mirrors of societal moral standards: reflection of cultural divergence and agreement across ethical topics
AI Meets Antimatter: Unveiling Antihydrogen Annihilations
Generative Language Models Potential for Requirement Engineering Applications: Insights into Current Strengths and Limitations
Large Language Models as Mirrors of Societal Moral Standards
WAFFLE: Multimodal Floorplan Understanding in the Wild
Construction of generalized samplets in Banach spaces
BIGCity: A Universal Spatiotemporal Model for Unified Trajectory and Traffic State Data Analysis
ESCAPE: Equivariant Shape Completion via Anchor Point Encoding
Uhura: A Benchmark for Evaluating Scientific Question Answering and Truthfulness in Low-Resource African Languages
Calibration through the Lens of Interpretability
QABISAR: Query-Article Bipartite Interactions for Statutory Article Retrieval
FIction: 4D Future Interaction Prediction from Video
A Deep Generative Model for the Design of Synthesizable Ionizable Lipids
Ref-GS: Directional Factorization for 2D Gaussian Splatting
Tomographic SAR Reconstruction for Forest Height Estimation
DPE-Net: Dual-Parallel Encoder Based Network for Semantic Segmentation of Polyps
Playable Game Generation
Leveraging Intermediate Neural Collapse with Simplex ETFs for Efficient Deep Neural Networks
Lightweight Contenders: Navigating Semi-Supervised Text Mining through Peer Collaboration and Self Transcendence
SyncVIS: Synchronized Video Instance Segmentation
Beyond Pixels: Text Enhances Generalization in Real-World Image Restoration
KnowledgePrompts: Exploring the Abilities of Large Language Models to Solve Proportional Analogies via Knowledge-Enhanced Prompting
Quantifying perturbation impacts for large language models
Explicit and data-Efficient Encoding via Gradient Flow
Thermal Vision: Pioneering Non-Invasive Temperature Tracking in Congested Spaces
Toward Real-Time Edge AI: Model-Agnostic Task-Oriented Communication with Visual Feature Alignment
Deep evolving semi-supervised anomaly detection
Coherent Video Inpainting Using Optical Flow-Guided Efficient Diffusion
K-UD: Revising Korean Universal Dependencies Guidelines
DynSUP: Dynamic Gaussian Splatting from An Unposed Image Pair
SAGA: Surface-Aligned Gaussian Avatar
DVasMesh: Deep Structured Mesh Reconstruction from Vascular Images for Dynamics Modeling of Vessels
AniMer: Animal Pose and Shape Estimation Using Family Aware Transformer
SPILDL: A Scalable and Parallel Inductive Learner in Description Logic
Categorical Keypoint Positional Embedding for Robust Animal Re-Identification
Motion-Aware Optical Camera Communication with Event Cameras
Vid-Morp: Video Moment Retrieval Pretraining from Unlabeled Videos in the Wild
Long text outline generation: Chinese text outline based on unsupervised framework and large language mode
Generative Model for Synthesizing Ionizable Lipids: A Monte Carlo Tree Search Approach
HT-HEDL: High-Throughput Hypothesis Evaluation in Description Logic

All 152