Papers

New on arXiv

Fri 19 Jan 2024

190 papers

SocraSynth: Multi-LLM Reasoning with Conditional StatisticsLLM reasoning → Reasoning for agents, planning and code
Stochastic Dynamic Power Dispatch with High Generalization and Few-Shot Adaption via Contextual Meta Graph Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
Dynamic Semantic Compression for CNN Inference in Multi-access Edge Computing: A Graph Reinforcement Learning-based AutoencoderDeep reinforcement learning methods → RL for energy, networks and operations
Image Safeguarding: Reasoning with Conditional Vision Language Model and Obfuscating Unsafe Content CounterfactuallyLLM reasoning → Reasoning for agents, planning and code +1
Communication Efficient and Provable Federated UnlearningLLM safety and security → Federated unlearning and poisoning
Synthesizing Moving People with 3D ControlDiffusion models → 3D, point cloud and scene generation
Reinforcement learning for question answering in programming domain using public community scoring as a human feedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
Pruning for Protection: Increasing Jailbreak Resistance in Aligned LLMs Without Fine-TuningLLM safety and security → Jailbreaking
Understanding Video Transformers via Universal Concept DiscoveryMechanistic interpretability → Interpreting vision and multimodal models
Deep Reinforcement Learning Empowered Activity-Aware Dynamic Health Monitoring SystemsDeep reinforcement learning methods → RL for clinical treatment and surgery
Sat2Scene: 3D Urban Scene Generation from Satellite Images with DiffusionDiffusion models → 3D, point cloud and scene generation
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding HeadsEfficient LLM inference and serving → Speculative decoding
FinLLMs: A Framework for Financial Reasoning Dataset Generation with Large Language ModelsLLM reasoning → Reasoning for agents, planning and code
MLLM-Tool: A Multimodal Large Language Model For Tool Agent LearningMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
Q&A Prompts: Discovering Rich Visual Clues through Mining Question-Answer Prompts for VQA requiring Diverse World KnowledgeLLM reasoning → Multimodal reasoning +1
Weakly Supervised Gaussian Contrastive Grounding with Large Multimodal Models for Video Question AnsweringMultimodal LLMs / vision-language models → Video understanding with MLLMs
Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion ModelOffline RL and imitation learning from data → Safe offline RL
LangBridge: Multilingual Reasoning Without Multilingual SupervisionLLM reasoning → Reasoning benchmarks and evaluation
Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language ModelsLLM safety and security → Prompt injection and agent security
PHOENIX: Open-Source Language Adaption for Direct Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making AgentsLLM reasoning → Reasoning for agents, planning and code +1
MAEDiff: Masked Autoencoder-enhanced Diffusion Models for Unsupervised Anomaly Detection in Brain ImagesDiffusion models → Medical imaging and segmentation
Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image SequencesLLM reasoning → Multimodal reasoning +1
Episodic Reinforcement Learning with Expanded State-reward SpaceDeep reinforcement learning methods → Deep RL algorithms and representations
Enhancing Scalability in Recommender Systems through Lottery Ticket Hypothesis and Knowledge Distillation-based Neural Network PruningKnowledge distillation → Distillation for recommender systems
Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step ReasoningLLM reasoning → Test-time compute and efficient thinking
CBVS: A Large-Scale Chinese Image-Text Benchmark for Real-World Short Video Search ScenariosMultimodal LLMs / vision-language models → Video understanding with MLLMs
DeepEdit: Knowledge Editing as Decoding with ConstraintsLLM reasoning → Knowledge- and tool-augmented reasoning
Contrastive Unlearning: A Contrastive Approach to Machine UnlearningLLM safety and security → Machine unlearning
Large Language Models are Efficient Learners of Noise-Robust Speech RecognitionLLM reasoning → Audio-language model reasoning
Interactive Mars Image Content-Based Search with Interpretable Machine Learning
Pragmatic Goal-Oriented Communications under Semantic-Effectiveness Channel Errors
A novel method to compute the contact surface area between an organ and cancer tissue
MB-RACS: Measurement-Bounds-based Rate-Adaptive Image Compressed Sensing Network
EEG Based Generative Depression Discriminator
Multidimensional Gabor-Like Filters Derived from Gaussian Functions on Logarithmic Frequency Axes
MDGNN: Multi-Relational Dynamic Graph Neural Network for Comprehensive and Dynamic Stock Investment Prediction
Quantifying Similarity: Text-Mining Approaches to Evaluate ChatGPT and Google Bard Content in Relation to BioMedical Literature
RSCNet: Dynamic CSI Compression for Cloud-based WiFi Sensing
A Unified Gaussian Process for Branching and Nested Hyperparameter Optimization
Language models align with human judgments on key grammatical constructions
Combining topic modelling and citation network analysis to study case law from the European Court on Human Rights on the right to respect for private and family life
A Volumetric Saliency Guided Image Summarization for RGB-D Indoor Scene Classification
Harnessing Neuron Stability to Improve DNN Verification
Progressive Distillation Based on Masked Generation Feature Method for Knowledge Graph Completion
Quantised Neural Network Accelerators for Low-Power IDS in Automotive Networks
Spatial Scaper: A Library to Simulate and Augment Soundscapes for Sound Event Localization and Detection in Realistic Rooms
A distribution-guided Mapper algorithm
The Surprising Harmfulness of Benign Overfitting for Adversarial Robustness
A Lightweight FPGA-based IDS-ECU Architecture for Automotive CAN
Memorization in Self-Supervised Learning Improves Downstream Generalization
Learned Image resizing with efficient training (LRET) facilitates improved performance of large-scale digital histopathology image classification models
PhotoBot: Reference-Guided Interactive Photography via Natural Language
Mining experimental data from Materials Science literature with Large Language Models: an evaluation study
PubTator 3.0: an AI-powered Literature Resource for Unlocking Biomedical Knowledge
Preservation of Feature Stability in Machine Learning Under Data Uncertainty for Decision Support in Critical Domains
Equivariant Graph Neural Operator for Modeling 3D Dynamics
FAIR Enough: How Can We Develop and Assess a FAIR-Compliant Dataset for Large Language Models' Training?
Exploring Highly Quantised Neural Networks for Intrusion Detection in Automotive CAN
Analysis and Detection of Multilingual Hate Speech Using Transformer Based Deep Learning
Revealing Emotional Clusters in Speaker Embeddings: A Contrastive Learning Strategy for Speech Emotion Recognition
When the Universe is Too Big: Bounding Consideration Probabilities for Plackett-Luce Rankings
Helmholtz-Decomposition and Optical Flow: A new method to characterize GCamP recordings
Fast Registration of Photorealistic Avatars for VR Facial Animation
The Radiation Oncology NLP Database
Provably Scalable Black-Box Variational Inference with Structured Variational Families
T2MAC: Targeted and Trusted Multi-Agent Communication through Selective Engagement and Evidence-Driven Integration
Clustering Molecular Energy Landscapes by Adaptive Network Embedding
MacroSwarm: A Field-based Compositional Framework for Swarm Programming
Decentralizing Coordination in Open Vehicle Fleets for Scalable and Dynamic Task Allocation
One Step Learning, One Step Review
AI Revolution on Chat Bot: Evidence from a Randomized Controlled Experiment
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
Event detection from novel data sources: Leveraging satellite imagery alongside GPS traces
SCENES: Subpixel Correspondence Estimation With Epipolar Supervision
The Cadaver in the Machine: The Social Practices of Measurement and Validation in Motion Capture Technology
Applications of flow models to the generation of correlated lattice QCD ensembles
Ensembler: Protect Collaborative Inference Privacy from Model Inversion Attack via Selective Ensemble
Motion Consistency Loss for Monocular Visual Odometry with Attention-Based Deep Learning
Advancements in eHealth Data Analytics through Natural Language Processing and Deep Learning
Source-Free and Image-Only Unsupervised Domain Adaptation for Category Level Object Pose Estimation
Using LLMs to discover emerging coded antisemitic hate-speech in extremist social media
Recent Advances in Named Entity Recognition: A Comprehensive Survey and Comparative Study
ActAnywhere: Subject-Aware Video Background Generation
Optimisation in Neurosymbolic Learning Systems
Co-Pilot for Health: Personalized Algorithmic AI Nudging to Improve Health Outcomes
Exploring scalable medical image encoders beyond text supervision
Simulation Based Bayesian Optimization
Neglected Hessian component explains mysteries in Sharpness regularization
Learning to Visually Connect Actions and their Effects
Estimation of AMOC transition probabilities using a machine learning based rare-event algorithm
Novel Representation Learning Technique using Graphs for Performance Analytics
Early alignment in two-layer networks training is a two-edged sword
Measuring the Impact of Scene Level Objects on Object Detection: Towards Quantitative Explanations of Detection Decisions
Metric Dynamic Equilibrium Logic
Determination of efficiency indicators of the stand for intelligent control of manual operations in industrial production
Knowledge Verification to Nip Hallucination in the Bud
Starlit: Privacy-Preserving Federated Learning to Enhance Financial Fraud Detection
NN-VVC: Versatile Video Coding boosted by self-supervisedly learned image coding for machines
Interactions with Prompt Problems: A New Way to Teach Programming with Large Language Models

All 190