Papers

New on arXiv

Thu 28 Dec 2023

187 papers

Any-point Trajectory Modeling for Policy LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
3VL: Using Trees to Improve Vision-Language Models' InterpretabilityMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Optimizing watermarks for large language modelsLLM safety and security → Watermarking generated content and models
Enhancing Open-Domain Task-Solving Capability of LLMs via Autonomous Tool Integration from GitHubLLM agents and tool use → General LLM agent frameworks and benchmarks
iFusion: Inverting Diffusion for Pose-Free Reconstruction from Sparse ViewsDiffusion models → 3D, point cloud and scene generation
Do Androids Know They're Only Dreaming of Electric Sheep?Mechanistic interpretability → Hallucination detection from model internals
Rethinking Model-based, Policy-based, and Value-based Reinforcement Learning via the Lens of Representation ComplexityLLM reasoning → Reinforcement learning for reasoning
LISA++: An Improved Baseline for Reasoning Segmentation with Large Language ModelLLM reasoning → Multimodal reasoning
Fast Inference of Mixture-of-Experts Language Models with OffloadingMixture-of-experts → Efficient MoE training and inference systems
Personalized Restoration via Dual-Pivot TuningDiffusion models → Inverse problems and image restoration
Gradient-based Planning with World ModelsWorld models → Latent dynamics models and model-based RL
4DGen: Grounded 4D Content Generation with Spatial-temporal ConsistencyDiffusion models → 3D, point cloud and scene generation
Visual Explanations of Image-Text Representations via Multi-Modal Information Bottleneck AttributionMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Can Active Sampling Reduce Causal Confusion in Offline Reinforcement Learning?Offline RL and imitation learning from data → Offline RL algorithms
Restoration by Generation with Constrained PriorsDiffusion models → Inverse problems and image restoration
LLM4Causal: Democratized Causal Tools for Everyone via Large Language ModelLLM agents and tool use → Medical and scientific domain agents
Grounding-Prompter: Prompting LLM with Multimodal Information for Temporal Sentence Grounding in Long VideosLLM reasoning → Multimodal reasoning
MIVC: Multiple Instance Visual Component for Visual-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model EvaluationLLM reasoning → Reasoning benchmarks and evaluation
FILP-3D: Enhancing 3D Few-shot Class-incremental Learning with Pre-trained Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
FedSDD: Scalable and Diversity-enhanced Distillation for Model Aggregation in Federated LearningKnowledge distillation → Federated, robust and private distillation
Experiential Co-Learning of Software-Developing AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
Joint Learning for Scattered Point Cloud Understanding with Hierarchical Self-DistillationKnowledge distillation → Detection and dense prediction distillation
DiffKG: Knowledge Graph Diffusion Model for RecommendationDiffusion models → Diffusion recommenders
MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile DevicesMultimodal LLMs / vision-language models → Visual token pruning and efficiency
TinyGPT-V: Efficient Multimodal Large Language Model via Small BackbonesMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Agnostic Interactive Imitation Learning: New Theory and Practical AlgorithmsOffline RL and imitation learning from data → Imitation learning methods
DiffusionGAN3D: Boosting Text-guided 3D Generation and Domain Adaptation by Combining 3D GANs and Diffusion PriorsDiffusion models → 3D, point cloud and scene generation
Layer Attack Unlearning: Fast and Accurate Machine Unlearning via Layer Level Attack and Knowledge DistillationLLM safety and security → Machine unlearning +1
Temporal Knowledge Distillation for Time-Sensitive Financial Services ApplicationsKnowledge distillation → Detection and dense prediction distillation
ZONE: Zero-Shot Instruction-Guided Local EditingMultimodal LLMs / vision-language models → Image editing and quality assessment +1
Universal Syntactic Structures: Modeling Syntax for Various Natural Languages
Maintaining User Trust Through Multistage Uncertainty Aware Inference
Hybrid quantum cycle generative adversarial network for small molecule generation
LLM4EDA: Emerging Progress in Large Language Models for Electronic Design Automation
Fast gradient-free activation maximization for neurons in spiking neural networks
Multimodal Sentiment Analysis with Missing Modality: A Knowledge-Transfer Approach
DrugAssist: A Large Language Model for Molecule Optimization
AdaMR: Adaptable Molecular Representation for Unified Pre-training Strategy
On the Three Demons in Causality in Finance: Time Resolution, Nonstationarity, and Latent Factors
Fast Quantum Convolutional Neural Networks for Low-Complexity Object Detection in Autonomous Driving Applications
CycleGAN Models for MRI Image Translation
Learning Vision from Models Rivals Learning Vision from Data
Classifier-free graph diffusion for molecular property targeting
Analyzing and Enhancing the Backward-Pass Convergence of Unrolled Optimization
Hotspot Prediction of Severe Traffic Accidents in the Federal District of Brazil
Discovery of Small Ultra-short-period Planets Orbiting KG Dwarfs in Kepler Survey Using GPU Phase Folding and Deep Learning Detection System
Beyond PID Controllers: PPO with Neuralized PID Policy for Proton Beam Intensity Control in Mu2e
SANIA: Polyak-type Optimization Framework Leads to Scale Invariant Stochastic Algorithms
Graph Learning in 4D: a Quaternion-valued Laplacian to Enhance Spectral GCNs
The Duck's Brain: Training and Inference of Neural Networks in Modern Database Engines
Towards Auto-Modeling of Formal Verification for NextG Protocols: A Multimodal cross- and self-attention Large Language Model Approach
Language Model as an Annotator: Unsupervised Context-aware Quality Phrase Generation
A randomized algorithm to solve reduced rank operator regression
STanHop: Sparse Tandem Hopfield Model for Memory-Enhanced Time Series Prediction
AQUALLM: Audio Question Answering Data Generation Using Large Language Models
SentinelLMs: Encrypted Input Adaptation and Fine-tuning of Language Models for Private and Secure Inference
Exploring Nature: Datasets and Models for Analyzing Nature-Related Disclosures
PINN surrogate of Li-ion battery models for parameter inference. Part II: Regularization and application of the pseudo-2D model
Improving Image Restoration through Removing Degradations in Textual Representations
Count What You Want: Exemplar Identification and Few-shot Counting of Human Actions in the Wild
PINN surrogate of Li-ion battery models for parameter inference. Part I: Implementation and multi-fidelity hierarchies for the single-particle model
Gradient Flossing: Improving Gradient Descent through Dynamic Control of Jacobians
Explainability-Based Adversarial Attack on Graphs Through Edge Perturbation
Improving Intrusion Detection with Domain-Invariant Representation Learning in Latent Space
Empirical fits to inclusive electron-carbon scattering data obtained by deep-learning methods
Structured Packing in LLM Training Improves Long Context Utilization
μGUIDE: a framework for quantitative imaging via generalized uncertainty-driven inference using deep learning
Effect of dimensionality change on the bias of word embeddings
Predicting Parkinson's disease evolution using deep learning
AI Content Self-Detection for Transformer-based Large Language Models
Comparative study of clustering models for multivariate time series from connected medical devices
Understanding Distributed Representations of Concepts in Deep Neural Networks without Supervision
Dynamic Decision Making in Engineering System Design: A Deep Q-Learning Approach
Intelligent Parsing: An Automated Parsing Framework for Extracting Design Semantics from E-commerce Creatives
Amodal Ground Truth and Completion in the Wild
The LLM Surgeon
Unsupervised Universal Image Segmentation
Learning to Generate Text in Arbitrary Writing Styles
Compact Neural Graphics Primitives with Learned Hash Probing
A Simple LLM Framework for Long-Range Video Question-Answering
Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labels
Think Before You Duel: Understanding Complexities of Preference Learning under Constrained Resources
SparseProp: Efficient Event-Based Simulation and Training of Sparse Recurrent Spiking Neural Networks
Continual Learning via Sequential Function-Space Variational Inference
EFHQ: Multi-purpose ExtremePose-Face-HQ dataset
Tractable Function-Space Variational Inference in Bayesian Neural Networks
Resilient Constrained Reinforcement Learning
HISR: Hybrid Implicit Surface Representation for Photorealistic 3D Human Reconstruction
Large-Vocabulary Segmentation for Medical Images with Text Prompts
Virtual Scientific Companion for Synchrotron Beamlines: A Prototype
Non-Vacuous Generalization Bounds for Large Language Models
Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action
Securing NextG Systems against Poisoning Attacks on Federated Learning: A Game-Theoretic Solution
FENet: Focusing Enhanced Network for Lane Detection
Function-Space Regularization in Neural Networks: A Probabilistic Perspective
Replica Tree-based Federated Learning using Limited Data
DreamGaussian4D: Generative 4D Gaussian Splatting
InsActor: Instruction-driven Physics-based Characters
ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe

All 187