Papers

New on arXiv

Sun 6 Oct 2024

156 papers

Polymath: A Challenging Multi-modal Mathematical Reasoning BenchmarkLLM reasoning → Multimodal reasoning +1
Core Knowledge Deficits in Multi-Modal Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Plausibly Problematic Questions in Multiple-Choice Benchmarks for Commonsense ReasoningLLM reasoning → Reasoning benchmarks and evaluation
Distributed Inference on Mobile Edge and Cloud: An Early Exit based Clustering ApproachEfficient LLM inference and serving → Early exit and edge inference
GreenLight-Gym: Reinforcement learning benchmark environment for control of greenhouse production systemsDeep reinforcement learning methods → RL for energy, networks and operations
AdaptDiff: Cross-Modality Domain Adaptation via Weak Conditional Semantic Diffusion for Retinal Vessel SegmentationDiffusion models → Medical imaging and segmentation
Unpacking Failure Modes of Generative Policies: Runtime Monitoring of Consistency and ProgressOffline RL and imitation learning from data → Language-conditioned policies and VLAs
Provable Weak-to-Strong Generalization via Benign OverfittingKnowledge distillation → General knowledge distillation methods
DeepLTL: Learning to Efficiently Satisfy Complex LTL Specifications for Multi-Task RLDeep reinforcement learning methods → Interpretable and logic-guided RL
Towards Unsupervised Blind Face Restoration using Diffusion PriorDiffusion models → Inverse problems and image restoration
Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHFLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
Hammer: Robust Function-Calling for On-Device Language Models via Function MaskingLLM agents and tool use → Tool learning and function calling
Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community RetrievalLLM reasoning → Clinical and biomedical applications
Bisimulation metric for Model Predictive ControlDeep reinforcement learning methods → Deep RL algorithms and representations
Pullback Flow Matching on Data ManifoldsDiffusion models → Flow matching, time series and science
FAMMA: A Benchmark for Financial Domain Multilingual Multimodal Question AnsweringLLM reasoning → Reasoning for agents, planning and code
MC-CoT: A Modular Collaborative CoT Framework for Zero-shot Medical-VQA with LLM and MLLM IntegrationMultimodal LLMs / vision-language models → Medical vision-language models
A Reinforcement Learning Engine with Reduced Action and State Space for Scalable Cyber-Physical Optimal ResponseDeep reinforcement learning methods → RL for energy, networks and operations
DAMRO: Dive into the Attention Mechanism of LVLM to Reduce Object HallucinationMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
Realizing Video Summarization from the Path of Language-based Semantic UnderstandingMixture-of-experts → Vision mixture-of-experts
ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error DetectionLLM reasoning → Mathematical reasoning +1
LRHP: Learning Representations for Human Preferences via Preference PairsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
AdaMemento: Adaptive Memory-Assisted Policy Optimization for Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
Interpret Your Decision: Logical Reasoning Regularization for Generalization in Visual ClassificationLLM reasoning → Multimodal reasoning
Learning to Solve Abstract Reasoning Problems with Neurosymbolic Program Synthesis and Task GenerationMechanistic interpretability → Steering and interpreting LLM reasoning
SITCOM: Step-wise Triple-Consistent Diffusion Sampling for Inverse ProblemsDiffusion models → Inverse problems and image restoration
Revisiting In-context Learning Inference Circuit in Large Language ModelsMechanistic interpretability → Probing deception, bias and beliefs
Large Language Model Inference Acceleration: A Comprehensive Hardware PerspectiveEfficient LLM inference and serving → Serving systems and request scheduling
Wrong-of-Thought: An Integrated Reasoning Framework with Multi-Perspective Verification and Wrong InformationLLM reasoning → Prompting and chain-of-thought reasoning
Improved Off-policy Reinforcement Learning in Biological Sequence DesignDeep reinforcement learning methods → RL for energy, networks and operations
MindScope: Exploring cognitive biases in large language models through Multi-Agent SystemsLLM agents and tool use → Social simulation and multi-agent debate
Attention Shift: Steering AI Away from Unsafe ContentLLM safety and security → Vision-language and text-to-image safety
G"odel Agent: A Self-Referential Agent Framework for Recursive Self-ImprovementLLM agents and tool use → General LLM agent frameworks and benchmarks +1
Empowering Backbone Models for Visual Text Generation with Input Granularity Control and Glyph-Aware TrainingDiffusion models → Image generation, text-to-image and editing
CAPEEN: Image Captioning with Early Exits and Knowledge DistillationEfficient LLM inference and serving → Early exit and edge inference +1
CoVLM: Leveraging Consensus from Vision-Language Models for Semi-supervised Multi-modal Fake News DetectionMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
DAdEE: Unsupervised Domain Adaptation in Early Exit PLMsEfficient LLM inference and serving → Early exit and edge inference
Long-context Language Models Fail in Basic Retrieval Tasks Without Sufficient Reasoning StepsLLM reasoning → Reasoning benchmarks and evaluation
SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model InferenceMultimodal LLMs / vision-language models → Visual token pruning and efficiency
Geometric Analysis of Reasoning Trajectories: A Phase Space Approach to Understanding Valid and Invalid Multi-Hop Reasoning in LLMsLLM reasoning → Test-time compute and efficient thinking
Lens: Rethinking Multilingual Enhancement for Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
DiffusionFake: Enhancing Generalization in Deepfake Detection via Guided Stable DiffusionDiffusion models → Image generation, text-to-image and editing
DABI: Evaluation of Data Augmentation Methods Using Downsampling in Bilateral Control-Based Imitation Learning with ImagesOffline RL and imitation learning from data → Robot manipulation imitation learning
VideoGuide: Improving Video Diffusion Models without Training Through a Teacher's GuideDiffusion models → Video generation
GenSim: A General Social Simulation Platform with Large Language Model based AgentsWorld models → World models for language agents +1
TIS-DPO: Token-level Importance Sampling for Direct Preference Optimization With Estimated WeightsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Permutative Preference Alignment from Listwise Ranking of Human JudgmentsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Inference Scaling for Long-Context Retrieval Augmented GenerationRetrieval-augmented generation → Generation and context integration
Toward Debugging Deep Reinforcement Learning Programs with RLExplorerDeep reinforcement learning methods → Deep RL algorithms and representations
Data-driven Under Frequency Load Shedding Using Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
Large Language Models for Knowledge-Free Network Management: Feasibility Study and Opportunities
Representing Web Applications As Knowledge Graphs
Large Scale MRI Collection and Segmentation of Cirrhotic Liver
Universal Approximation of Mean-Field Models via Transformers
Hawk: An Efficient NALM System for Accurate Low-Power Appliance Recognition
An evaluation of LLM code generation capabilities through graded exercises
Accelerating Biological Spatial Cluster Analysis with the Parallel Integral Image Technique
Comparing Zealous and Restrained AI Recommendations in a Real-World Human-AI Collaboration Task
Mitigating Hallucinations Using Ensemble of Knowledge Graph and Vector Store in Large Language Models to Enhance Mental Health Support
SafeLLM: Domain-Specific Safety Monitoring for Large Language Models: A Case Study of Offshore Wind Maintenance
LLM Gesticulator: Leveraging Large Language Models for Scalable and Controllable Co-Speech Gesture Synthesis
On the Reliability of Large Language Models to Misinformed and Demographically-Informed Prompts
Continuous Approximations for Improving Quantization Aware Training of LLMs
Diagnosing Robotics Systems Issues with Large Language Models
Evaluating the Correctness of Inference Patterns Used by LLMs for Judgment
TA3: Testing Against Adversarial Attacks on Machine Learning Models
A Global Cybersecurity Standardization Framework for Healthcare Informatics
VPI-Mlogs: A web-based machine learning solution for applications in petrophysics
Taylor Unswift: Secured Weight Release for Large Language Models via Taylor Expansion
Graph Fourier Neural Kernels (G-FuNK): Learning Solutions of Nonlinear Diffusive Parametric PDEs on Multiple Domains
Multimodal 3D Fusion and In-Situ Learning for Spatially Aware AI
Mode-GS: Monocular Depth Guided Anchored 3D Gaussian Splatting for Robust Ground-View Scene Rendering
The Optimization Landscape of SGD Across the Feature Learning Strength
Radial Basis Operator Networks
Multi-Tiered Self-Contrastive Learning for Medical Microwave Radiometry (MWR) Breast Cancer Detection
Is What You Ask For What You Get? Investigating Concept Associations in Text-to-Image Models
A Cross-Lingual Meta-Learning Method Based on Domain Adaptation for Speech Emotion Recognition
Control Large Language Models via Divide and Conquer
Punctuation Prediction for Polish Texts using Transformers
Passage Retrieval of Polish Texts Using OKAPI BM25 and an Ensemble of Cross Encoders
Evaluation of Code LLMs on Geospatial Code Generation
Can LLMs Improve Multimodal Fact-Checking by Asking Relevant Questions?
VISTA: A Visual and Textual Attention Dataset for Interpreting Multimodal Models
ProtoMed-LLM: An Automatic Evaluation Framework for Large Language Models in Medical Protocol Formulation
Towards the first UD Treebank of Spoken Italian: the KIParla forest
Upsample or Upweight? Balanced Training on Heavily Imbalanced Datasets
Robustness Reprogramming for Representation Learning
Enhancing 3D Human Pose Estimation Amidst Severe Occlusion with Dual Transformer Fusion
EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles
Watermarking Decision Tree Ensembles
Ranking Policy Learning via Marketplace Expected Value Estimation From Observational Data
GAMformer: Bridging Tabular Foundation Models and Interpretable Machine Learning
textttdattri: A Library for Efficient Data Attribution
Modeling Social Media Recommendation Impacts Using Academic Networks: A Graph Neural Network Approach
Social Choice for Heterogeneous Fairness in Recommendation
Learning De-Biased Representations for Remote-Sensing Imagery
How Does the Disclosure of AI Assistance Affect the Perceptions of Writing?
Generative Flows on Synthetic Pathway for Drug Design
On Evaluating LLMs' Capabilities as Functional Approximators: A Bayesian Perspective
YanTian: An Application Platform for AI Global Weather Forecasting Models

All 156