Papers

New on arXiv

Thu 18 Jan 2024

231 papers

Veagle: Advancements in Multimodal Representation LearningMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Inflation with Diffusion: Efficient Temporal Adaptation for Text-to-Video Super-ResolutionDiffusion models → Video generation
Foundation Models in Federated Learning: Assessing Backdoor VulnerabilitiesLLM safety and security → Federated unlearning and poisoning
Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine UnlearningLLM safety and security → Machine unlearning
LangProp: A code optimization framework using Large Language Models applied to drivingEnd-to-end autonomous driving → Large language models for driving
Hacking Predictors Means Hacking Cars: Using Sensitivity Analysis to Identify Trajectory Prediction Vulnerabilities for Autonomous Driving SecurityEnd-to-end autonomous driving → Adversarial scenarios and safety testing
A Simple Latent Diffusion Approach for Panoptic Segmentation and Mask InpaintingDiffusion models → Medical imaging and segmentation
Towards Language-Driven Video Inpainting via Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Image editing and quality assessment
ChatQA: Surpassing GPT-4 on Conversational QA and RAGRetrieval-augmented generation → RAG robustness and adaptive retrieval
Motion-Zero: Zero-Shot Moving Object Control Framework for Diffusion-Based Video GenerationDiffusion models → Video generation
CLIP feature-based randomized control using images and text for multiple tasks and robotsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Code Prompting Elicits Conditional Reasoning Abilities in Text+Code LLMsLLM reasoning → Prompting and chain-of-thought reasoning
DiffusionAgent: Navigating Expert Models for Agentic Image GenerationDiffusion models → Image generation, text-to-image and editing +1
GPT4Ego: Unleashing the Potential of Pre-trained Models for Zero-Shot Egocentric Action RecognitionMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Self-Rewarding Language ModelsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
R-Judge: Benchmarking Safety Risk Awareness for LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
Advancing Large Multi-modal Models with Explicit Chain-of-Reasoning and Visual Question GenerationLLM reasoning → Multimodal reasoning +1
WorldDreamer: Towards General World Models for Video Generation via Predicting Masked TokensWorld models → Video-generation world models and simulators
Towards Generative Abstract Reasoning: Completing Raven's Progressive Matrix via Rule Abstraction and SelectionLLM reasoning → Multimodal reasoning
CustomVideo: Customizing Text-to-Video Generation with Multiple SubjectsDiffusion models → Video generation
MAMBA: Multi-level Aggregation via Memory Bank for Video Object DetectionState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
Reconciling Spatial and Temporal Abstractions for Goal RepresentationDeep reinforcement learning methods → Deep RL algorithms and representations
Temporal Insight Enhancement: Mitigating Temporal Hallucination in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
All in How You Ask for It: Simple Black-Box Method for Jailbreak AttacksLLM safety and security → Jailbreaking
Wavelet-Guided Acceleration of Text Inversion in Diffusion-Based Image EditingDiffusion models → Image generation, text-to-image and editing
Robotic Test Tube Rearrangement Using Combined Reinforcement Learning and Motion PlanningDeep reinforcement learning methods → RL for robot locomotion and manipulation
Exploration and Anti-Exploration with Distributional Random Network DistillationDeep reinforcement learning methods → Deep RL algorithms and representations
Hijacking Attacks against Neural Networks by Analyzing Training DataLLM safety and security → Backdoor and data poisoning attacks
Offline Imitation Learning by Controlling the Effective Planning HorizonOffline RL and imitation learning from data → Imitation learning methods
SkyEyeGPT: Unifying Remote Sensing Vision-Language Tasks via Instruction Tuning with Large Language ModelMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Imitation Learning Inputting Image Feature to Each Layer of Neural NetworkOffline RL and imitation learning from data → Robot manipulation imitation learning
Harnessing Density Ratios for Online Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms +1
DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model ServingEfficient LLM inference and serving → Serving systems and request scheduling
Traffic Smoothing Controllers for Autonomous Vehicles Using Deep Reinforcement Learning and Real-World Trajectory DataEnd-to-end autonomous driving → Cooperative and V2X driving +1
Attention Based Molecule Generation via Hierarchical Variational Autoencoder
Unsupervised Motion Retargeting for Human-Robot Imitation
Interplay of Semantic Communication and Knowledge Learning
Legal and ethical implications of applications based on agreement technologies: the case of auction-based road intersections
Prerequisite Structure Discovery in Intelligent Tutoring Systems
A Comparison of Veterans with Problematic Opioid Use Identified through Natural Language Processing of Clinical Notes versus Using Diagnostic Codes
Harmonizing Code-mixed Conversations: Personality-assisted Code-mixed Response Generation in Dialogues
Automated Scoring of Clinical Patient Notes using Advanced NLP and Pseudo Labeling
Machine Learning Modeling Of SiRNA Structure-Potency Relationship With Applications Against Sars-Cov-2 Spike Gene
Disentangled Condensation for Large-scale Graphs
The Synergy Between Optimal Transport Theory and Multi-Agent Reinforcement Learning
Self context-aware emotion perception on human-robot interaction
Automatic dimensionality reduction of Twin-in-the-Loop Observers
Generalized Nested Rollout Policy Adaptation with Limited Repetitions
M3BUNet: Mobile Mean Max UNet for Pancreas Segmentation on CT-Scans
DataViz3D: An Novel Method Leveraging Online Holographic Modeling for Extensive Dataset Preprocessing and Visualization
Can Large Language Model Summarizers Adapt to Diverse Scientific Communication Goals?
Learning High-Quality and General-Purpose Phrase Representations
Differentially Private and Adversarially Robust Machine Learning: An Empirical Evaluation
Reconstructing the Invisible: Video Frame Restoration through Siamese Masked Conditional Variational Autoencoder
Analyzing and Mitigating Bias for Vulnerable Classes: Towards Balanced Representation in Dataset
Deep Dict: Deep Learning-based Lossy Time Series Compressor for IoT Data
Distribution Consistency based Self-Training for Graph Neural Networks with Sparse Labels
Natural Mitigation of Catastrophic Interference: Continual Learning in Power-Law Learning Environments
Noninvasive Acute Compartment Syndrome Diagnosis Using Random Forest Machine Learning
Approximation of Solution Operators for High-dimensional PDEs
Cooperative Multi-Agent Graph Bandits: UCB Algorithm and Regret Analysis
Agricultural Object Detection with You Look Only Once (YOLO) Algorithm: A Bibliometric and Systematic Literature Review
Harmonized Spatial and Spectral Learning for Robust and Generalized Medical Image Segmentation
MutaBot: A Mutation Testing Approach for Chatbots
Deep Generative Modeling for Financial Time Series with Application in VaR: A Comparative Review
Using LLM such as ChatGPT for Designing and Implementing a RISC Processor: Execution,Challenges and Limitations
Hierarchical Federated Learning in Multi-hop Cluster-Based VANETs
Excuse me, sir? Your language model is leaking (information)
Keeping Deep Learning Models in Check: A History-Based Approach to Mitigate Overfitting
Intelligent Optimization and Machine Learning Algorithms for Structural Anomaly Detection using Seismic Signals
Towards providing reliable job completion time predictions using PCS
Inconsistent dialogue responses and how to recover from them
Bridging Cultural Nuances in Dialogue Agents through Cultural Value Surveys
Exploring General Intelligence via Gated Graph Transformer in Functional Connectivity Studies
ELRT: Efficient Low-Rank Training for Compact Convolutional Neural Networks
MELODY: Robust Semi-Supervised Hybrid Model for Entity-Level Online Anomaly Detection with Multivariate Time Series
Noise Contrastive Estimation-based Matching Framework for Low-Resource Security Attack Pattern Recognition
Improving One-class Recommendation with Multi-tasking on Various Preference Intensities
Mathematical Algorithm Design for Deep Learning under Societal and Judicial Constraints: The Algorithmic Transparency Requirement
Physics-constrained convolutional neural networks for inverse problems in spatiotemporal partial differential equations
Personality Trait Inference Via Mobile Phone Sensors: A Machine Learning Approach
On the Readiness of Scientific Data for a Fair and Transparent Use in Machine Learning
A Hierarchical Framework with Spatio-Temporal Consistency Learning for Emergence Detection in Complex Adaptive Systems
An attempt to generate new bridge types from latent space of generative flow
Machine learning approach to detect dynamical states from recurrence measures
Learning Non-myopic Power Allocation in Constrained Scenarios
ParaHome: Parameterizing Everyday Home Activities Towards 3D Generative Modeling of Human-Object Interactions
OMG-Seg: Is One Model Good Enough For All Segmentation?
RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything
The Manga Whisperer: Automatically Generating Transcriptions for Comics
Supervised Fine-tuning in turn Improves Visual Foundation Models
AutoFT: Learning an Objective for Robust Fine-Tuning
Edit One for All: Interactive Batch Image Editing
Explaining the Implicit Neural Canvas: Connecting Pixels to Neurons by Tracing their Contributions
Enabling Efficient Equivariant Operations in the Fourier Basis via Gaunt Tensor Products
GPAvatar: Generalizable and Precise Head Avatar from Image(s)
MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizer
Eclectic Rule Extraction for Explainability of Deep Neural Network based Intrusion Detection Systems
Maximal-Capacity Discrete Memoryless Channel Identification
Divide and not forget: Ensemble of selectively trained experts in Continual Learning

All 231