Papers

New on arXiv

Sun 8 Dec 2024

134 papers

Mean--Variance Portfolio Selection by Continuous-Time Reinforcement Learning: Algorithms, Regret Analysis, and Empirical StudyDeep reinforcement learning methods → Adversarial robustness and RL in finance
Learning to Correction: Explainable Feedback Generation for Visual Commonsense Reasoning DistractorLLM reasoning → Multimodal reasoning +1
Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM QuantizationEfficient LLM inference and serving → KV cache quantization
GL-Fusion: Rethinking the Combination of Graph Neural Network and Large Language modelLLM reasoning → Knowledge- and tool-augmented reasoning
Classifier-free guidance in LLMs SafetyLLM safety and security → Machine unlearning
7B Fully Open Source Moxin-LLM/VLM -- From Pretraining to GRPO-based Reinforcement Learning EnhancementLLM reasoning → Reasoning benchmarks and evaluation
Trust No AI: Prompt Injection Along The CIA Security TriadLLM safety and security → Prompt injection and agent security
GraPE: A Generate-Plan-Edit Framework for Compositional T2I SynthesisDiffusion models → Image generation, text-to-image and editing
Are foundation models for computer vision good conformal predictors?Multimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
Mixture-of-PageRanks: Replacing Long-Context with Real-Time, Sparse GraphRAGRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
Latent-Reframe: Enabling Camera Control for Video Diffusion Model without TrainingDiffusion models → Video generation
SparseDiT: Token Sparsification for Efficient Diffusion TransformerDiffusion models → Diffusion foundations and sampling
Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video GenerationDiffusion models → Video generation
Post-hoc Probabilistic Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
TopoCellGen: Generating Histopathology Cell Topology with a Diffusion ModelDiffusion models → Medical imaging and segmentation
Does RLHF Scale? Exploring the Impacts From Data, Model, and MethodLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
Nested Diffusion Models Using Hierarchical Latent PriorsDiffusion models → Diffusion foundations and sampling
Chimera: Improving Generalist Model with Domain-Specific ExpertsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Anti-Reference: Universal and Immediate Defense Against Reference-Based GenerationDiffusion models → Robustness, privacy and adversarial aspects
Language hooks: a modular framework for augmenting LLM reasoning that decouples tool usage from the model and its promptLLM reasoning → Reasoning for agents, planning and code +1
Towards Modeling Human-Agentic Collaborative Workflows: A BPMN ExtensionLLM agents and tool use → Software engineering coding agents
Exploring Multi-Grained Concept Annotations for Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Accelerating Manufacturing Scale-Up from Material Discovery Using Agentic Web Navigation and Retrieval-Augmented AI for Process Engineering Schematics DesignLLM agents and tool use → Medical and scientific domain agents
Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language ModelsLLM safety and security → Vision-language and text-to-image safety
Text-to-3D Generation by 2D EditingDiffusion models → 3D, point cloud and scene generation
BiDM: Pushing the Limit of Quantization for Diffusion ModelsDiffusion models → Diffusion foundations and sampling
Reinforcement Learning for a Discrete-Time Linear-Quadratic Control Problem with an ApplicationDeep reinforcement learning methods → RL theory and sample complexity
Accelerating Video Diffusion Models via Distribution MatchingDiffusion models → Video generation
XKV: Personalized KV Cache Memory Reduction for Long-Context LLM InferenceEfficient LLM inference and serving → KV cache optimization
doScenes: An Autonomous Driving Dataset with Natural Language Instruction for Human Interaction and Vision-Language NavigationEnd-to-end autonomous driving → Reasoning VLA and VLM driving policies
PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity MaximizationMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
3D-Consistent Image Inpainting with Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
MG-3D: Multi-Grained Knowledge-Enhanced 3D Medical Vision-Language Pre-trainingMultimodal LLMs / vision-language models → Medical vision-language models
Cooperative SQL Generation for Segmented Databases By Using Multi-functional LLM AgentsLLM agents and tool use → Web, search, and research agents
MotionStone: Decoupled Motion Intensity Modulation with Diffusion Transformer for Image-to-Video GenerationDiffusion models → Video generation
A Collaborative Multi-Agent Approach to Retrieval-Augmented Generation Across Diverse DataRetrieval-augmented generation → Agentic RAG, agents and memory +1
CSG: A Context-Semantic Guided Diffusion Approach in De Novo Musculoskeletal Ultrasound Image GenerationDiffusion models → Medical imaging and segmentation
SABER: Model-agnostic Backdoor Attack on Chain-of-Thought in Neural Code GenerationLLM reasoning → Reasoning for agents, planning and code +1
Self-Guidance: Boosting Flow and Diffusion Generation on Their OwnDiffusion models → Diffusion foundations and sampling
An Entailment Tree Generation Approach for Multimodal Multi-Hop Question Answering with Mixture-of-Experts and Iterative Feedback MechanismMixture-of-experts → MoE large language models
[CLS] Token Tells Everything Needed for Training-free Efficient MLLMsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image GenerationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
On diffusion posterior sampling via sequential Monte Carlo for zero-shot scaffolding of protein motifsDiffusion models → Flow matching, time series and science
Two-way Deconfounder for Off-policy Evaluation in Causal Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
Open-Source Acceleration of Stable-Diffusion.cpp Deployable on All DevicesDiffusion models → Diffusion foundations and sampling
BudgetFusion: Perceptually-Guided Adaptive Diffusion ModelsDiffusion models → Diffusion foundations and sampling
Strategizing Equitable Transit Evacuations: A Data-Driven Reinforcement Learning ApproachDeep reinforcement learning methods → RL for autonomous driving and traffic
Policy-shaped prediction: avoiding distractions in model-based reinforcement learningDeep reinforcement learning methods → RL for robot locomotion and manipulation
From Critique to Clarity: A Pathway to Faithful and Personalized Code Explanations with Large Language Models
EEG-Based Mental Imagery Task Adaptation via Ensemble of Weight-Decomposed Low-Rank Adapters
Experimenting with Multi-modal Information to Predict Success of Indian IPOs
Towards AI-45circ Law: A Roadmap to Trustworthy AGI
Evaluating Robustness of LLMs on Crisis-Related Microblogs across Events, Information Types, and Linguistic Features
Pre-trained protein language model for codon optimization
Language Model as Visual Explainer
Comb Tensor Networks vs. Matrix Product States: Enhanced Efficiency in High-Dimensional Spaces
Incentivized Symbiosis: A Paradigm for Human-Agent Coevolution
Tube Loss: A Novel Approach for Prediction Interval Estimation
EGEAN: An Exposure-Guided Embedding Alignment Network for Post-Click Conversion Estimation
M3-20M: A Large-Scale Multi-Modal Molecule Dataset for AI-driven Drug Design and Discovery
Infusing Prompts with Syntax and Semantics
Efficient Context Propagating Perceiver Architectures for Auto-Regressive Language Modeling
Fully Distributed Online Training of Graph Neural Networks in Networked Systems
Self-supervised cost of transport estimation for multimodal path planning
ENCO: Life-Cycle Management of Enterprise-Grade Copilots
Order Theory in the Context of Machine Learning
Measuring Grammatical Diversity from Small Corpora: Derivational Entropy Rates, Mean Length of Utterances, and Annotation Invariance
A4-Unet: Deformable Multi-Scale Attention Network for Brain Tumor Segmentation
Ethnography and Machine Learning: Synergies and New Directions
GVDepth: Zero-Shot Monocular Depth Estimation for Ground Vehicles based on Probabilistic Cue Fusion
Learning from Snapshots of Discrete and Continuous Data Streams
Hyperspectral Image Spectral-Spatial Feature Extraction via Tensor Principal Component Analysis
KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models
Stochastic Gradient Descent Revisited
Fuzzy Norm-Explicit Product Quantization for Recommender Systems
Implicit Delta Learning of High Fidelity Neural Network Potentials
On Socially Fair Low-Rank Approximation and Column Subset Selection
Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond
Steering Large Language Models to Evaluate and Amplify Creativity
Dilated Balanced Cross Entropy Loss for Medical Image Segmentation
Cloud Platforms for Developing Generative AI Solutions: A Scoping Review of Tools and Services
The AI Double Standard: Humans Judge All AIs for the Actions of One
Vision Transformer-based Semantic Communications With Importance-Aware Quantization
Can Generative AI Solve Your In-Context Learning Problem? A Martingale Perspective
New Additive OCBA Procedures for Robust Ranking and Selection
Imputation Matters: A Deeper Look into an Overlooked Step in Longitudinal Health and Behavior Sensing Research
siForest: Detecting Network Anomalies with Set-Structured Isolation Forest
1-800-SHARED-TASKS at RegNLP: Lexical Reranking of Semantic Retrieval (LeSeR) for Regulatory Question Answering
Enhancing Content Representation for AR Image Quality Assessment Using Knowledge Distillation
Paddy Disease Detection and Classification Using Computer Vision Techniques: A Mobile Application to Detect Paddy Disease
PIG: Physics-Informed Gaussians as Adaptive Parametric Mesh Representations
LightOcc: Lightweight Spatial Embedding for Efficient Vision-based 3D Occupancy Prediction
Efficient Semantic Splatting for Remote Sensing Multi-view Segmentation
LVS-Net: A Lightweight Vessels Segmentation Network for Retinal Image Analysis
A Cross-Validation Study of Turkish Sentiment Analysis Datasets and Tools
FOF-X: Towards Real-time Detailed Human Reconstruction from a Single Image
When Vision Models Meet Parameter Efficient Look-Aside Adapters Without Large-Scale Audio Pretraining
Materials-Discovery Workflows Guided by Symbolic Regression: Identifying Acid-Stable Oxides for Electrocatalysis
Adversarial Transferability in Deep Denoising Models: Theoretical Insights and Robustness Enhancement via Out-of-Distribution Typical Set Sampling
Accurate Multi-Category Student Performance Forecasting at Early Stages of Online Education Using Neural Networks

All 134