Papers

New on arXiv

Sun 22 Dec 2024

164 papers

Evaluating LLM Reasoning in the Operations Research Domain with ORQALLM reasoning → Mathematical reasoning
Enhancing Item Tokenization for Generative Recommendation through Self-ImprovementSynthetic data and self-improvement for LLMs → LLM synthetic data generation
Generative Diffusion Modeling: A Practical HandbookDiffusion models → Diffusion foundations and sampling
Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow MatchingDiffusion models → Image generation, text-to-image and editing
A Multi-AI Agent System for Autonomous Optimization of Agentic AI Solutions via Iterative Refinement and LLM-Driven Feedback LoopsLLM agents and tool use → General LLM agent frameworks and benchmarks
LLM Agent for Fire Dynamics SimulationsLLM agents and tool use → Web, search, and research agents
Fairness in Reinforcement Learning with Bisimulation MetricsDeep reinforcement learning methods → RL for games and combinatorial optimization
Adam on Local Time: Addressing Nonstationarity in RL with Relative Adam TimestepsDeep reinforcement learning methods → Deep RL algorithms and representations
Similarity Trajectories: Linking Sampling Process to Artifacts in Diffusion-Generated ImagesDiffusion models → Diffusion foundations and sampling
Multi-Agent Sampling: Scaling Inference Compute for Data Synthesis with Tree Search-Based Agentic CollaborationLLM agents and tool use → General LLM agent frameworks and benchmarks +1
ViLBias: Detecting and Reasoning about Bias in Multimodal ContentLLM reasoning → Multimodal reasoning
Adapting Image-to-Video Diffusion Models for Large-Motion Frame InterpolationDiffusion models → Video generation
Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language ModelsLLM safety and security → Jailbreaking
A Reality Check on Context Utilisation for Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
GraphAgent: Agentic Graph Language AssistantLLM agents and tool use → Web, search, and research agents
Expert Routing with Synthetic Data for Continual LearningMixture-of-experts → Mixture of LoRA experts
PromptDresser: Improving the Quality and Controllability of Virtual Try-On via Generative Textual Prompt and Prompt-aware MaskDiffusion models → 3D, point cloud and scene generation
Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
Part-Of-Speech Sensitivity of Routers in Mixture of Experts ModelsMixture-of-experts → Expert routing strategies
A Research Agenda for Usability and Generalisation in Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
System-2 Mathematical Reasoning via Enriched Instruction TuningLLM reasoning → Mathematical reasoning
Aristotle: Mastering Logical Reasoning with A Logic-Complete Decompose-Search-Resolve FrameworkLLM reasoning → Reasoning benchmarks and evaluation
FADA: Fast Diffusion Avatar Synthesis with Mixed-Supervised Multi-CFG DistillationDiffusion models → Audio, speech and music
Map Imagination Like Blind Humans: Group Diffusion Model for Robotic Map GenerationDiffusion models → 3D, point cloud and scene generation
Self-Corrected Flow Distillation for Consistent One-Step and Few-Step Text-to-Image GenerationDiffusion models → Flow matching, time series and science
Temporal-Frequency State Space Duality: An Efficient Paradigm for Speech Emotion RecognitionState-space sequence models (S4, Mamba) → Speech and audio SSMs
Online Preference-based Reinforcement Learning with Self-augmented Feedback from Large Language ModelLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
Teaching LLMs to Refine with ToolsLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
CoF: Coarse to Fine-Grained Image Understanding for Multi-modal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Diffusion-Based Approaches in Medical Image Generation and AnalysisDiffusion models → Medical imaging and segmentation
Adversarially Domain-adaptive Latent Diffusion for Unsupervised Semantic SegmentationDiffusion models → Medical imaging and segmentation
GME: Improving Universal Multimodal Retrieval by Multimodal LLMsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
OpenRFT: Adapting Reasoning Foundation Model for Domain-specific Tasks with Reinforcement Fine-TuningLLM reasoning → Reinforcement learning for reasoning
ACL-QL: Adaptive Conservative Level in Q-Learning for Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
Online Learning from Strategic Human Feedback in LLM Fine-TuningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
KG4Diagnosis: A Hierarchical Multi-Agent LLM Framework with Knowledge Graph Enhancement for Medical DiagnosisLLM agents and tool use → Medical and scientific domain agents
Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion TransformersDiffusion models → Diffusion foundations and sampling +1
ABACUS: A FinOps Service for Cloud Cost Optimization
Engineering Carbon Credits Towards A Responsible FinTech Era: The Practices, Implications, and Future
Bridging Auditory Perception and Language Comprehension through MEG-Driven Encoding Models
Reduced Order Models and Conditional Expectation -- Analysing Parametric Low-Order Approximations
Multi-Agent Q-Learning for Real-Time Load Balancing User Association and Handover in Mobile Networks
RoboSignature: Robust Signature and Watermarking on Network Attacks
Joint Knowledge Editing for Information Enrichment and Probability Promotion
Talking with Tables for Better LLM Factual Data Interactions
Hierarchically Gated Experts for Efficient Online Continual Learning
Foundation Model for Lossy Compression of Spatiotemporal Scientific Data
Nonlinear thermodynamic computing out of equilibrium
Gaussian and Bootstrap Approximation for Matching-based Average Treatment Effect Estimators
COVID-19 on YouTube: A Data-Driven Analysis of Sentiment, Toxicity, and Content Recommendations
WPMixer: Efficient Multi-Resolution Mixing for Long-Term Time Series Forecasting
DCC: Differentiable Cardinality Constraints for Partial Index Tracking
Where Did Your Model Learn That? Label-free Influence for Self-supervised Learning
Survey on Abstractive Text Summarization: Dataset, Models, and Metrics
Analysis of Speech Temporal Dynamics in the Context of Speaker Verification and Voice Anonymization
Semantic Web: Past, Present, and Future (with Machine Learning on Knowledge Graphs and Language Models on Knowledge Graphs)
The Potential of Convolutional Neural Networks for Cancer Detection
Unifying Feature-Based Explanations with Functional ANOVA and Cooperative Game Theory
ASP-based Multi-shot Reasoning via DLV2 with Incremental Grounding
AI-Based Teat Shape and Skin Condition Prediction for Dairy Management
Style Transfer Dataset: What Makes A Good Stylization?
Empirical evaluation of normalizing flows in Markov Chain Monte Carlo
LLMsAgainstHate @ NLU of Devanagari Script Languages 2025: Hate Speech Detection and Target Identification in Devanagari Languages via Parameter Efficient Fine-Tuning of LLMs
Lies, Damned Lies, and Distributional Language Statistics: Persuasion and Deception with Large Language Models
Scalable Speech Enhancement with Dynamic Channel Pruning
Fair and Accurate Regression: Strong Formulations and Algorithms
Decentralized Governance of Autonomous AI Agents
Learning to Adapt to Low-Resource Paraphrase Generation
Grams: Gradient Descent with Adaptive Momentum Scaling
Refining CNN-based Heatmap Regression with Gradient-based Corner Points for Electrode Localization
DreamOmni: Unified Image Generation and Editing
Analysis on LLMs Performance for Code Summarization
SAIL: Sample-Centric In-Context Learning for Document Information Extraction
MARINA-P: Superior Performance in Non-smooth Federated Optimization with Adaptive Stepsizes
Aligning Graphical and Functional Causal Abstractions
SubstationAI: Multimodal Large Model-Based Approaches for Analyzing Substation Equipment Faults
Iterative NLP Query Refinement for Enhancing Domain-Specific Information Retrieval: A Case Study in Career Services
Decoupled Functional Central Limit Theorems for Two-Time-Scale Stochastic Approximation
Optimizing Data Curation through Spectral Analysis and Joint Batch Selection (SALN)
Interactive Classification Metrics: A graphical application to build robust intuition for classification model evaluation
Computational Analysis of Character Development in Holocaust Testimonies
The HalluRAG Dataset: Detecting Closed-Domain Hallucinations in RAG Applications Using an LLM's Internal States
Differentially Private Random Block Coordinate Descent
DR-Encoder: Encode Low-rank Gradients with Random Prior for Large Language Models Differentially Privately
Modular Conversational Agents for Surveys and Interviews
Why Do Speech Language Models Fail to Generate Semantically Coherent Outputs? A Modality Evolving Perspective
An OpenMind for 3D medical vision self-supervised learning
HyperNet Fields: Efficiently Training Hypernetworks without Ground Truth by Learning Weight Trajectories
ErasableMask: A Robust and Erasable Privacy Protection Scheme against Black-box Face Recognition Models
MINTQA: A Multi-Hop Question Answering Benchmark for Evaluating LLMs on New and Tail Knowledge
Parameter-Efficient Interventions for Enhanced Model Merging
FriendsQA: A New Large-Scale Deep Video Understanding Dataset with Fine-grained Topic Categorization for Story Videos
Reversed Attention: On The Gradient Descent Of Attention Layers In GPT
GAS: Generative Auto-bidding with Post-training Search
Robustness of Large Language Models Against Adversarial Attacks
Data value estimation on private gradients
Where am I? Cross-View Geo-localization with Natural Language Descriptions
Solving Nonlinear Energy Supply and Demand System Using Physics-Informed Neural Networks
Multi-Scale Foreground-Background Confidence for Out-of-Distribution Segmentation
Pinwheel-shaped Convolution and Scale-based Dynamic Loss for Infrared Small Target Detection

All 164