Papers

New on arXiv

Sat 15 Feb 2025

143 papers

How Blind and Low-Vision Individuals Prefer Large Vision-Language Model-Generated Scene DescriptionsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
CalibQuant: 1-Bit KV Cache Quantization for Multimodal LLMsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
A Closer Look at System Prompt RobustnessLLM safety and security → Prompt injection and agent security
Self-supervised Attribute-aware Dynamic Preference Ranking AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Boosting Cross-problem Generalization in Diffusion-Based Neural Combinatorial Solver via Inference Time AdaptationDiffusion models → Diffusion foundations and sampling
D-CIPHER: Dynamic Collaborative Intelligent Multi-Agent System with Planner and Heterogeneous Executors for Offensive SecurityLLM agents and tool use → Agent threats, guardrails and governance
Probing Semantic Routing in Large Mixture-of-Expert ModelsMixture-of-experts → Expert routing strategies
LLM-driven Knowledge Distillation for Dynamic Text-Attributed GraphsKnowledge distillation → Graph neural network distillation
MET-Bench: Multimodal Entity Tracking for Evaluating the Limitations of Vision-Language and Reasoning ModelsWorld models → World models for language agents +1
CiteCheck: Towards Accurate Citation Faithfulness DetectionRetrieval-augmented generation → RAG robustness and adaptive retrieval
A Tutorial on LLM Reasoning: Relevant Methods behind ChatGPT o1LLM reasoning → Test-time compute and efficient thinking
Accelerated co-design of robots through morphological pretrainingDeep reinforcement learning methods → RL for robot locomotion and manipulation
Is Depth All You Need? An Exploration of Iterative Reasoning in LLMsLLM reasoning → Prompting and chain-of-thought reasoning
Divergent Thoughts toward One Goal: LLM-based Multi-Agent Collaboration System for Electronic Design AutomationLLM reasoning → Reasoning for agents, planning and code +1
SkyReels-A1: Expressive Portrait Animation in Video Diffusion TransformersDiffusion models → Audio, speech and music
Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning
SVBench: A Benchmark with Temporal Multi-Turn Dialogues for Streaming Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
Distraction is All You Need for Multimodal Large Language Model JailbreakingMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
Tackling the Zero-Shot Reinforcement Learning Loss DirectlyDeep reinforcement learning methods → Deep RL algorithms and representations
Which Features are Best for Successor Features?Deep reinforcement learning methods → Deep RL algorithms and representations
The Philosophical Foundations of Growing AI Like A ChildLLM reasoning → Reasoning benchmarks and evaluation
Rule-Bottleneck Reinforcement Learning: Joint Explanation and Decision Optimization for Resource Allocation with Language AgentsLLM agents and tool use → Reinforcement learning for LLM agents +1
Improving Retrieval-Augmented Deep Assertion Generation via Joint TrainingRetrieval-augmented generation → RAG for code
CLoCKDistill: Consistent Location-and-Context-aware Knowledge Distillation for DETRsKnowledge distillation → Detection and dense prediction distillation
Dataset Protection via Watermarked Canaries in Retrieval-Augmented LLMsRetrieval-augmented generation → Privacy and security of RAG +1
Pushing up to the Limit of Memory Bandwidth and Capacity Utilization for Efficient LLM Decoding on Embedded FPGAEfficient LLM inference and serving → Serving systems and request scheduling
USER-VLM 360: Personalized Vision Language Models with User-aware Tuning for Social Human-Robot InteractionsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Privacy Preservation through Practical Machine UnlearningLLM safety and security → Machine unlearning
Retrieval-augmented Encoders for Extreme Multi-label Text ClassificationRetrieval-augmented generation → Generation and context integration
Asymptotic evaluation of the information processing capacity in reservoir computing
Exploring the Role of Artificial Intelligence and Machine Learning in Process Optimization for Chemical Industry
Breast Lump Detection and Localization with a Tactile Glove Using Deep Learning
Pulmonary Tuberculosis Edge Diagnosis System Based on MindSpore Framework: Low-cost and High-precision Implementation with Ascend 310 Chip
SEM-CLIP: Precise Few-Shot Learning for Nanoscale Defect Detection in Scanning Electron Microscope Image
Regularizacc~ao, aprendizagem profunda e interdisciplinaridade em problemas inversos mal-postos
GeneralizeFormer: Layer-Adaptive Model Generation across Test-Time Distribution Shifts
AI and the Law: Evaluating ChatGPT's Performance in Legal Classification
AnyTouch: Learning Unified Static-Dynamic Representation across Multiple Visuo-tactile Sensors
Hallucinations are inevitable but can be made statistically negligible
E2CB2former: Effecitve and Explainable Transformer for CB2 Receptor Ligand Activity Prediction
Large Language Models for Extrapolative Modeling of Manufacturing Processes
Fundamental Principles of Linguistic Structure are Not Represented by o3
Reduced Order Modeling with Shallow Recurrent Decoder Networks
The underlying structures of self-attention: symmetry, directionality, and emergent dynamics in Transformer training
Evolving Hate Speech Online: An Adaptive Framework for Detection and Mitigation
Do Deepfake Detectors Work in Reality?
An Open-Source Web-Based Tool for Evaluating Open-Source Large Language Models Leveraging Information Retrieval from Custom Documents
Automatic Quality Assessment of First Trimester Crown-Rump-Length Ultrasound Images
PCGRLLM: Large Language Model-Driven Reward Design for Procedural Content Generation Reinforcement Learning
Breaking Down the Hierarchy: A New Approach to Leukemia Classification
Developing Conversational Speech Systems for Robots to Detect Speech Biomarkers of Cognition in People Living with Dementia
Bridging the Sim-to-Real Gap for Athletic Loco-Manipulation
RemInD: Remembering Anatomical Variations for Interpretable Domain Adaptive Medical Image Segmentation
Learning Identifiable Structures Helps Avoid Bias in DNN-based Supervised Causal Learning
Broadcast Channel Cooperative Gain: An Operational Interpretation of Partial Information Decomposition
Super Resolution image reconstructs via total variation-based image deconvolution: a majorization-minimization approach
A Geometric Approach to Personalized Recommendation with Set-Theoretic Constraints Using Box Embeddings
Layerwise Recall and the Geometry of Interwoven Knowledge in LLMs
NitiBench: A Comprehensive Study of LLM Framework Capabilities for Thai Legal Question Answering
Towards Effective Extraction and Evaluation of Factual Claims
Multilingual Encoder Knows more than You Realize: Shared Weights Pretraining for Extremely Low-Resource Languages
To Bin or not to Bin: Alternative Representations of Mass Spectra
Implicit Neural Representations of Molecular Vector-Valued Functions
LEAPS: A discrete neural sampler via locally equivariant networks
Mobile Robotic Multi-View Photometric Stereo
Generalizable speech deepfake detection via meta-learned LoRA
The Vendiscope: An Algorithmic Microscope For Data Collections
E-3DGS: Event-Based Novel View Rendering of Large-Scale Scenes Using 3D Gaussian Splatting
Improved Offline Contextual Bandits with Second-Order Bounds: Betting and Freezing
MITRE ATT&CK Applications in Cybersecurity and The Way Forward
NeuroAMP: A Novel End-to-end General Purpose Deep Neural Amplifier for Personalized Hearing Aids
On Vanishing Gradients, Over-Smoothing, and Over-Squashing in GNNs: Bridging Recurrent and Graph Learning
BalanceBenchmark: A Survey for Multimodal Imbalance Learning
Transformer-Driven Modeling of Variable Frequency Features for Classifying Student Engagement in Online Learning
HybriDNA: A Hybrid Transformer-Mamba2 Long-Range DNA Language Model
Beyond Known Fakes: Generalized Detection of AI-Generated Images via Post-hoc Distribution Alignment
CoCoEvo: Co-Evolution of Programs and Test Cases to Enhance Code Generation
FaceSwapGuard: Safeguarding Facial Privacy from DeepFake Threats through Identity Obfuscation
Dynamic Influence Tracker: Measuring Time-Varying Sample Influence During Training
ReReLRP -- Remembering and Recognizing Tasks with LRP
Epidemic-guided deep learning for spatiotemporal forecasting of Tuberculosis outbreak
REGNav: Room Expert Guided Image-Goal Navigation
Preconditioned Inexact Stochastic ADMM for Deep Model
A Distillation-based Future-aware Graph Neural Network for Stock Trend Prediction
Evaluating improvements on using Large Language Models (LLMs) for property extraction in the Open Research Knowledge Graph (ORKG)
Learning to Explain Air Traffic Situation
Bone Soups: A Seek-and-Soup Model Merging Approach for Controllable Multi-Objective Generation
Why is prompting hard? Understanding prompts on binary sequence predictors
Human-Centric Community Detection in Hybrid Metaverse Networks with Integrated AI Entities
LoRE-Merging: Exploring Low-Rank Estimation For Large Language Model Merging
1bit-Merging: Dynamic Quantized Merging for Large Language Models
BASE-SQL: A powerful open source Text-To-SQL baseline approach
Beyond One-Size-Fits-All Pruning via Evolutionary Metric Search for Large Language Models
VarGes: Improving Variation in Co-Speech 3D Gesture Generation via StyleCLIPS
PropNet: a White-Box and Human-Like Network for Sentence Representation
Semantics-aware Test-time Adaptation for 3D Human Pose Estimation
A Mathematics Framework of Artificial Shifted Population Risk and Its Further Understanding Related to Consistency Regularization
A Comprehensive Survey of Deep Learning for Multivariate Time Series Forecasting: A Channel Strategy Perspective
NPSim: Nighttime Photorealistic Simulation From Daytime Images With Monocular Inverse Rendering and Ray Tracing
Hyperdimensional Intelligent Sensing for Efficient Real-Time Audio Processing on Extreme Edge

All 143