1d ago 90
ZebraPose: Zebra Detection and Pose Estimation using only Synthetic Data
ZebraPose: Zebra Detection and Pose Estimation using only Synthetic Data
1d ago 90
Enhancing Inverse Reinforcement Learning through Encoding Dynamic Information in Reward Shaping
Enhancing Inverse Reinforcement Learning through Encoding Dynamic Information in Reward Shaping
1d ago 90
When Speculation Spills Secrets: Side Channels via Speculative Decoding In LLMs
When Speculation Spills Secrets: Side Channels via Speculative Decoding In LLMs
1d ago 90
Symmetrization Weighted Binary Cross-Entropy: Modeling Perceptual Asymmetry for Human-Consistent Neural Edge Detection
Symmetrization Weighted Binary Cross-Entropy: Modeling Perceptual Asymmetry for Human-Consistent Neural Edge Detection
1d ago 90
Multi-Objective Bayesian Optimization for Networked Black-Box Systems: A Path to Greener Profits and Smarter Designs
Multi-Objective Bayesian Optimization for Networked Black-Box Systems: A Path to Greener Profits and Smarter Designs
1d ago 90
from Benign import Toxic: Jailbreaking the Language Model via Adversarial Metaphors
from Benign import Toxic: Jailbreaking the Language Model via Adversarial Metaphors
1d ago 90
Fixing the Broken Compass: Diagnosing and Improving Inference-Time Reward Modeling
Fixing the Broken Compass: Diagnosing and Improving Inference-Time Reward Modeling
1d ago 90
GenDR: Lighten Generative Detail Restoration
GenDR: Lighten Generative Detail Restoration
1d ago 90
Convergence and Connectivity: Dynamics of Multi-Agent Q-Learning in Random Networks
Convergence and Connectivity: Dynamics of Multi-Agent Q-Learning in Random Networks
1d ago 90
LLM-Mediated Guidance of MARL Systems
LLM-Mediated Guidance of MARL Systems
1d ago 90
MTBench: A Multimodal Time Series Benchmark for Temporal Reasoning and Question Answering
MTBench: A Multimodal Time Series Benchmark for Temporal Reasoning and Question Answering
1d ago 90
Efficient IoT Intrusion Detection with an Improved Attention-Based CNN-BiLSTM Architecture
Efficient IoT Intrusion Detection with an Improved Attention-Based CNN-BiLSTM Architecture
1d ago 90
Localized Graph-Based Neural Dynamics Models for Terrain Manipulation
Localized Graph-Based Neural Dynamics Models for Terrain Manipulation
1d ago 90
Geospatial Representation Learning: A Survey from Deep Learning to The LLM Era
Geospatial Representation Learning: A Survey from Deep Learning to The LLM Era
1d ago 90
Spatiotemporal Field Generation Based on Hybrid Mamba-Transformer with Physics-informed Fine-tuning
Spatiotemporal Field Generation Based on Hybrid Mamba-Transformer with Physics-informed Fine-tuning
1d ago 90
ZeroTuning: Unlocking the Initial Token's Power to Enhance Large Language Models Without Training
ZeroTuning: Unlocking the Initial Token's Power to Enhance Large Language Models Without Training
1d ago 90
Intrinsic Self-Correction in LLMs: Towards Explainable Prompting via Mechanistic Interpretability
Intrinsic Self-Correction in LLMs: Towards Explainable Prompting via Mechanistic Interpretability
1d ago 90
Attributing Response to Context: A Jensen-Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generation
Attributing Response to Context: A Jensen-Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generation
1d ago 90
Unveiling the "Fairness Seesaw": Discovering and Mitigating Gender and Race Bias in Vision-Language Models
Unveiling the "Fairness Seesaw": Discovering and Mitigating Gender and Race Bias in Vision-Language Models
1d ago 90
Can LLMs Reason Structurally? Benchmarking via the Lens of Data Structures
Can LLMs Reason Structurally? Benchmarking via the Lens of Data Structures
1d ago 90
Cross-Attention Speculative Decoding
Cross-Attention Speculative Decoding
1d ago 90
Belief-Based Offline Reinforcement Learning for Delay-Robust Policy Optimization
Belief-Based Offline Reinforcement Learning for Delay-Robust Policy Optimization
1d ago 90
Algorithmically Establishing Trust in Evaluators
Algorithmically Establishing Trust in Evaluators
1d ago 90
Uni-DPO: A Unified Paradigm for Dynamic Preference Optimization of LLMs
Uni-DPO: A Unified Paradigm for Dynamic Preference Optimization of LLMs
1d ago 90
Complexity of normalized stochastic first-order methods with momentum under heavy-tailed noise
Complexity of normalized stochastic first-order methods with momentum under heavy-tailed noise
1d ago 90
LighthouseGS: Indoor Structure-aware 3D Gaussian Splatting for Panorama-Style Mobile Captures
LighthouseGS: Indoor Structure-aware 3D Gaussian Splatting for Panorama-Style Mobile Captures
1d ago 90
A New Dataset and Performance Benchmark for Real-time Spacecraft Segmentation in Onboard Computers
A New Dataset and Performance Benchmark for Real-time Spacecraft Segmentation in Onboard Computers
1d ago 90
Shuffle-R1: Efficient RL framework for Multimodal Large Language Models via Data-centric Dynamic Shuffle
Shuffle-R1: Efficient RL framework for Multimodal Large Language Models via Data-centric Dynamic Shuffle
1d ago 90
MME-Emotion: A Holistic Evaluation Benchmark for Emotional Intelligence in Multimodal Large Language Models
MME-Emotion: A Holistic Evaluation Benchmark for Emotional Intelligence in Multimodal Large Language Models
1d ago 90
AI Agentic Vulnerability Injection And Transformation with Optimized Reasoning
AI Agentic Vulnerability Injection And Transformation with Optimized Reasoning
1d ago 90
AUDETER: A Large-scale Dataset for Deepfake Audio Detection in Open Worlds
AUDETER: A Large-scale Dataset for Deepfake Audio Detection in Open Worlds
1d ago 90
The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward
The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward
1d ago 90
ButterflyQuant: Ultra-low-bit LLM Quantization through Learnable Orthogonal Butterfly Transforms
ButterflyQuant: Ultra-low-bit LLM Quantization through Learnable Orthogonal Butterfly Transforms
1d ago 90
Self-Augmented Robot Trajectory: Efficient Imitation Learning via Safe Self-augmentation with Demonstrator-annotated Precision
Self-Augmented Robot Trajectory: Efficient Imitation Learning via Safe Self-augmentation with Demonstrator-annotated Precision
1d ago 90
Is In-Context Learning Learning?
Is In-Context Learning Learning?
1d ago 90
TableDART: Dynamic Adaptive Multi-Modal Routing for Table Understanding
TableDART: Dynamic Adaptive Multi-Modal Routing for Table Understanding
1d ago 90
MaskVCT: Masked Voice Codec Transformer for Zero-Shot Voice Conversion With Increased Controllability via Multiple Guidances
MaskVCT: Masked Voice Codec Transformer for Zero-Shot Voice Conversion With Increased Controllability via Multiple Guidances
1d ago 90
HuMam: Humanoid Motion Control via End-to-End Deep Reinforcement Learning with Mamba
HuMam: Humanoid Motion Control via End-to-End Deep Reinforcement Learning with Mamba
1d ago 90
Bridging Fairness and Explainability: Can Input-Based Explanations Promote Fairness in Hate Speech Detection?
Bridging Fairness and Explainability: Can Input-Based Explanations Promote Fairness in Hate Speech Detection?
1d ago 90
Beyond Aggregation: Guiding Clients in Heterogeneous Federated Learning
Beyond Aggregation: Guiding Clients in Heterogeneous Federated Learning
1d ago 90
Understanding Language Prior of LVLMs by Contrasting Chain-of-Embedding
Understanding Language Prior of LVLMs by Contrasting Chain-of-Embedding
1d ago 90
HarmMetric Eval: Benchmarking Metrics and Judges for LLM Harmfulness Assessment
HarmMetric Eval: Benchmarking Metrics and Judges for LLM Harmfulness Assessment
1d ago 90
Discrete Variational Autoencoding via Policy Search
Discrete Variational Autoencoding via Policy Search
1d ago 90
GLASS Flows: Transition Sampling for Alignment of Flow and Diffusion Models
GLASS Flows: Transition Sampling for Alignment of Flow and Diffusion Models
1d ago 90
VoiceBridge: Designing Latent Bridge Models for General Speech Restoration at Scale
VoiceBridge: Designing Latent Bridge Models for General Speech Restoration at Scale
1d ago 90
ACT: Agentic Classification Tree
ACT: Agentic Classification Tree
1d ago 90
Data Provenance Auditing of Fine-Tuned Large Language Models with a Text-Preserving Technique
Data Provenance Auditing of Fine-Tuned Large Language Models with a Text-Preserving Technique
1d ago 90
Learning under Quantization for High-Dimensional Linear Regression
Learning under Quantization for High-Dimensional Linear Regression
1d ago 90
Context-level Language Modeling by Learning Predictive Context Embeddings
Context-level Language Modeling by Learning Predictive Context Embeddings
1d ago 90
RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA
RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA