Papers

New on arXiv

Sat 1 Nov 2025

174 papers

Test-time Scaling of LLMs: A Survey from A Subproblem Structure PerspectiveLLM reasoning → Test-time compute and efficient thinking
Cognitively-Inspired Episodic Memory Architectures for Accurate and Efficient Character AIRetrieval-augmented generation → Agentic RAG, agents and memory
Retrieval-Augmented Generation of Pediatric Speech-Language Pathology vignettes: A Proof-of-Concept StudyRetrieval-augmented generation → Medical and biomedical RAG
Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
iFlyBot-VLA Technical ReportVision-language-action models → Generalist VLA models and benchmarks
EvoMem: Improving Multi-Agent Planning with Dual-Evolving MemoryLLM agents and tool use → Agent memory systems
Towards Understanding, Analyzing, and Optimizing Agentic AI Execution: A CPU-Centric PerspectiveLLM agents and tool use → Software engineering coding agents
Does RLVR Extend Reasoning Boundaries? Investigating Capability Expansion in Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
Inference-Time Chain-of-Thought Pruning with Latent Informativeness SignalsLLM reasoning → Test-time compute and efficient thinking
Do Methods to Jailbreak and Defend LLMs Generalize Across Languages?LLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
Evolve to Inspire: Novelty Search for Diverse Image GenerationDiffusion models → Image generation, text-to-image and editing
Outlier-Aware Post-Training Quantization for Image Super-ResolutionEfficient LLM inference and serving → KV cache quantization
ShadowLogic: Backdoors in Any Whitebox LLMLLM safety and security → Backdoor and data poisoning attacks
Reviving Stale Updates: Data-Free Knowledge Distillation for Asynchronous Federated LearningKnowledge distillation → Federated, robust and private distillation
Been There, Scanned That: Nostalgia-Driven LiDAR Compression for Self-Driving CarsEnd-to-end autonomous driving → End-to-end system architecture
Leveraging Multi-Agent System (MAS) and Fine-Tuned Small Language Models (SLMs) for Automated Telecom Network TroubleshootingLLM agents and tool use → Agentic AI for wireless networks
More Than A Shortcut: A Hyperbolic Approach To Early-Exit NetworksEfficient LLM inference and serving → Early exit and edge inference
DTS: Enhancing Large Reasoning Models via Decoding Tree SketchingLLM reasoning → Test-time compute and efficient thinking
AgentGit: A Version Control Framework for Reliable and Scalable LLM-Powered Multi-Agent SystemsLLM agents and tool use → Software engineering coding agents
Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation SteeringMechanistic interpretability → Activation steering methods
SpecDiff-2: Scaling Diffusion Drafter Alignment For Faster Speculative DecodingDiffusion models → Discrete and text diffusion +1
OpenSIR: Open-Ended Self-Improving ReasonerLLM reasoning → Reinforcement learning for reasoning +1
Agentic Auto-Scheduling: An Experimental Study of LLM-Guided Loop OptimizationLLM agents and tool use → Software engineering coding agents
Diagnosing Hallucination Risk in AI Surgical Decision-Support: A Sequential Framework for Sequential ValidationLLM reasoning → Hallucination detection and mitigation
Friend or Foe: How LLMs' Safety Mind Gets Fooled by Intent Shift AttackLLM safety and security → Jailbreaking
Improving Robustness to Out-of-Distribution States in Imitation Learning via Deep Koopman-Boosted Diffusion PolicyDiffusion models → Diffusion and flow policies for robotics +1
Red-teaming Activation Probes using Prompted LLMsLLM safety and security → Prompt injection and agent security
Single-agent Reinforcement Learning Model for Regional Adaptive Traffic Signal ControlDeep reinforcement learning methods → RL for autonomous driving and traffic
Robust Single-Agent Reinforcement Learning for Regional Traffic Signal Control Under Demand FluctuationsDeep reinforcement learning methods → RL for autonomous driving and traffic
Word Salad Chopper: Reasoning Models Waste A Ton Of Decoding Budget On Useless Repetitions, Self-KnowinglyLLM reasoning → Test-time compute and efficient thinking
SegDebias: Test-Time Bias Mitigation for ViT-Based CLIP via SegmentationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Reasoning Planning for Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
Issue-Oriented Agent-Based Framework for Automated Review Comment GenerationLLM agents and tool use → Software engineering coding agents
Reimagining Safety Alignment with An ImageLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
Zero-RAG: Towards Retrieval-Augmented Generation with Zero Redundant KnowledgeRetrieval-augmented generation → RAG pipeline design and evaluation
Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction ModelsDiffusion models → 3D, point cloud and scene generation
ToM: Leveraging Tree-oriented MapReduce for Long-Context Reasoning in Large Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning +1
textttReMind: Understanding Deductive Code Reasoning in LLMsLLM reasoning → Reasoning for agents, planning and code
FedMGP: Personalized Federated Learning with Multi-Group Text-Visual PromptsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
SmartDoc: A Context-Aware Agentic Method Comment Generation PluginLLM agents and tool use → Software engineering coding agents
DRIP: Defending Prompt Injection via Token-wise Representation Editing and Residual Instruction FusionLLM safety and security → Prompt injection and agent security
ToxicTextCLIP: Text-Based Poisoning and Backdoor Attacks on CLIP Pre-trainingMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
Enhancing Frequency Forgery Clues for Diffusion-Generated Image DetectionDiffusion models → Image generation, text-to-image and editing
Bootstrap Off-policy with World ModelWorld models → Latent dynamics models and model-based RL +1
MedRECT: A Medical Reasoning Benchmark for Error Correction in Clinical TextsLLM reasoning → Clinical and biomedical applications
LGCA: Enhancing Semantic Representation via Progressive ExpansionMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Tree Training: Accelerating Agentic LLMs Training via Shared Prefix ReuseLLM agents and tool use → General LLM agent frameworks and benchmarks
Quantum Machine Unlearning: Foundations, Mechanisms, and TaxonomyLLM safety and security → Machine unlearning
UME-R1: Exploring Reasoning-Driven Generative Multimodal EmbeddingsLLM reasoning → Multimodal reasoning +1
Saliency-R1: Incentivizing Unified Saliency Reasoning Capability in MLLM with Confidence-Guided Reinforcement LearningLLM reasoning → Multimodal reasoning +1
Rethinking Facial Expression Recognition in the Era of Multimodal Large Language Models: Benchmark, Datasets, and BeyondLLM reasoning → Audio-language model reasoning +1
Diverse Human Value Alignment for Large Language Models via Ethical ReasoningLLM reasoning → Reasoning benchmarks and evaluation +1
Reasoning Trajectories for Socratic Debugging of Student Code: From Misconceptions to Contradictions and Updated BeliefsLLM reasoning → Reasoning for agents, planning and code
Detecting AI-Generated Images via Diffusion Snap-Back Reconstruction: A Forensic ApproachDiffusion models → Image generation, text-to-image and editing
Reject Only Critical Tokens: Pivot-Aware Speculative DecodingEfficient LLM inference and serving → Speculative decoding
Exploiting Latent Space Discontinuities for Building Universal LLM Jailbreaks and Data Extraction AttacksLLM safety and security → Jailbreaking
LingGym: How Far Are LLMs from Thinking Like Field Linguists?LLM reasoning → Reasoning benchmarks and evaluation
Better Call CLAUSE: A Discrepancy Benchmark for Auditing LLMs Legal Reasoning CapabilitiesLLM reasoning → Reasoning for agents, planning and code
Sherlock: Reliable and Efficient Agentic Workflow ExecutionLLM reasoning → Reasoning for agents, planning and code +1
Enhancing failure prediction in nuclear industry: Hybridization of knowledge- and data-driven techniques
Data Analysis and Performance Evaluation of Simulation Deduction Based on LLMs
Agentic Educational Content Generation for African Languages on Edge Devices
Automated Invoice Data Extraction: Using LLM and OCR
Cross-Lingual SynthDocs: A Large-Scale Synthetic Corpus for Any to Arabic OCR and Document Understanding
multiMentalRoBERTa: A Fine-tuned Multiclass Classifier for Mental Health Disorder
Fibbinary-Based Compression and Quantization for Efficient Neural Radio Receivers
Superpositional Gradient Descent: Harnessing Quantum Principles for Model Training
Challenging DINOv3 Foundation Model under Low Inter-Class Variability: A Case Study on Fetal Brain Ultrasound
Delta-learned force fields for nonbonded interactions: Addressing the strength mismatch between covalent-nonbonded interaction for global models
Towards classification-based representation learning for place recognition on LiDAR scans
EP-HDC: Hyperdimensional Computing with Encrypted Parameters for High-Throughput Privacy-Preserving Inference
FeNN-DMA: A RISC-V SoC for SNN acceleration
Validating Deep Models for Alzheimer's 18F-FDG PET Diagnosis Across Populations: A Study with Latin American Data
Cross-Validated Causal Inference: a Modern Method to Combine Experimental and Observational Data
Enhancing Heavy Rain Nowcasting with Multimodal Data: Integrating Radar and Satellite Observations
TRISKELION-1: Unified Descriptive-Predictive-Generative AI
A Voice-Enabled Virtual Patient System for Interactive Training in Standardized Clinical Assessment
Polynomial Mixing Times of Simulated Tempering for Mixture Targets by Conductance Decomposition
Investigating the Robustness of Knowledge Tracing Models in the Presence of Student Concept Drift
Applying Medical Imaging Tractography Techniques to Painterly Rendering of Images
Privacy-Aware Time Series Synthesis via Public Knowledge Distillation
Toward Better Optimization of Low-Dose CT Enhancement: A Critical Analysis of Loss Functions and Image Quality Assessment Metrics
SOCRATES: Simulation Optimization with Correlated Replicas and Adaptive Trajectory Evaluations
Metadata-Aligned 3D MRI Representations for Contrast Understanding and Quality Control
Isotropic Curvature Model for Understanding Deep Learning Optimization: Is Gradient Orthogonalization Optimal?
Lifted Successor Generation in Numeric Planning
Filtered Neural Galerkin model reduction schemes for efficient propagation of initial condition uncertainties in digital twins
Sensitivity Analysis for Climate Science with Generative Flow Models
Lessons Learned from the Use of Generative AI in Engineering and Quality Assurance of a WEB System for Healthcare
Do You Know About My Nation? Investigating Multilingual Language Models' Cultural Literacy Through Factual Knowledge
Benchmarking individual tree segmentation using multispectral airborne laser scanning data: the FGI-EMIT dataset
Diluting Restricted Boltzmann Machines
Grounding Surgical Action Triplets with Instrument Instance Segmentation: A Dataset and Target-Aware Fusion Approach
Stochastic Shortest Path with Sparse Adversarial Costs
Node Preservation and its Effect on Crossover in Cartesian Genetic Programming
Modeling the Construction of a Literary Archetype: The Case of the Detective Figure in French Literature
Certain but not Probable? Differentiating Certainty from Probability in LLM Token Outputs for Probabilistic Scenarios
Gaining Momentum: Uncovering Hidden Scoring Dynamics in Hockey through Deep Neural Sequencing and Causal Modeling
CueBench: Advancing Unified Understanding of Context-Aware Video Anomalies in Real-World
PreferThinker: Reasoning-based Personalized Image Preference Assessment

All 174