Papers

New on arXiv

Tue 12 Aug 2025

355 papers

Deep Reinforcement Learning for Optimal Asset Allocation Using DDPG with TiDEDeep reinforcement learning methods → Adversarial robustness and RL in finance
A Hierarchical Signal Coordination and Control System Using a Hybrid Model-based and Reinforcement Learning ApproachDeep reinforcement learning methods → RL for autonomous driving and traffic
KG-o1: Enhancing Multi-hop Question Answering in Large Language Models via Knowledge Graph IntegrationLLM reasoning → Knowledge- and tool-augmented reasoning
Efficient Switchable Safety Control in LLMs via Magic-Token-Guided Co-TrainingLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
Toward Robust Semi-supervised Regression via Dual-stream Knowledge DistillationKnowledge distillation → General knowledge distillation methods
Toward Lifelong Learning in Equilibrium Propagation: Sleep-like and Awake Rehearsal for Enhanced StabilityDeep reinforcement learning methods → Deep RL algorithms and representations
KnowDR-REC: A Benchmark for Referring Expression Comprehension with Real-World KnowledgeLLM reasoning → Multimodal reasoning
PersRM-R1: Enhance Personalized Reward Modeling with Reinforcement LearningLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment +1
Large Language Models Show Signs of Alignment with Human Neurocognition During Abstract ReasoningLLM reasoning → Reasoning benchmarks and evaluation
NetMoniAI: An Agentic AI Framework for Network Security & MonitoringLLM agents and tool use → Agent threats, guardrails and governance
Securing Agentic AI: Threat Modeling and Risk Analysis for Network Monitoring Agentic AI SystemLLM agents and tool use → Agent threats, guardrails and governance
Understanding Dementia Speech Alignment with Diffusion-Based Image GenerationDiffusion models → Medical imaging and segmentation
Resurrecting the Salmon: Rethinking Mechanistic Interpretability with Domain-Specific Sparse AutoencodersLLM reasoning → Reasoning benchmarks and evaluation +1
CLF-RL: Control Lyapunov Function Guided Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
How Safe Will I Be Given What I Saw? Calibrated Prediction of Safety Chances for Image-Controlled AutonomyWorld models → Latent dynamics models and model-based RL
UltraLight Med-Vision Mamba for Classification of Neoplastic Progression in Tubular AdenomasState-space sequence models (S4, Mamba) → Mamba for medical image analysis
Lung-DDPM+: Efficient Thoracic CT Image Synthesis using Diffusion Probabilistic ModelDiffusion models → Medical imaging and segmentation
SegDAC: Visual Generalization in Reinforcement Learning via Dynamic Object TokensDeep reinforcement learning methods → RL for robot locomotion and manipulation
Fake-Mamba: Real-Time Speech Deepfake Detection Using Bidirectional Mamba as Self-Attention's AlternativeState-space sequence models (S4, Mamba) → Speech and audio SSMs
Can AI Keep a Secret? Contextual Integrity Verification: A Provable Security Architecture for LLMsLLM safety and security → Prompt injection and agent security
Distilling Reinforcement Learning into Single-Batch DatasetsDeep reinforcement learning methods → Deep RL algorithms and representations
Value Function Initialization for Knowledge Transfer and Jump-start in Deep Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
Beyond Blanket Masking: Examining Granularity for Privacy Protection in Images Captured by Blind and Low Vision UsersMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
FineState-Bench: A Comprehensive Benchmark for Fine-Grained State Control in GUI AgentsLLM agents and tool use → GUI and mobile agents
Cowpox: Towards the Immunity of VLM-based Multi-Agent SystemsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
Cluster Topology-Driven Placement of Experts Reduces Network Traffic in MoE InferenceMixture-of-experts → Efficient MoE training and inference systems
AMRG: Extend Vision Language Models for Automatic Mammography Report GenerationMultimodal LLMs / vision-language models → Medical vision-language models
Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language ModelsDiffusion models → Discrete and text diffusion
Training-Free Text-Guided Color Editing with Multi-Modal Diffusion TransformerDiffusion models → Image generation, text-to-image and editing
BrowseMaster: Towards Scalable Web Browsing via Tool-Augmented Programmatic Agent PairLLM agents and tool use → Web, search, and research agents
A Review On Safe Reinforcement Learning Using Lyapunov and Barrier FunctionsDeep reinforcement learning methods → Safe and constrained RL
LogicIF: Towards Complex Logic Instruction FollowingLLM agents and tool use → General LLM agent frameworks and benchmarks
OdysseyBench: Evaluating LLM Agents on Long-Horizon Complex Office Application WorkflowsLLM agents and tool use → General LLM agent frameworks and benchmarks
OpenCUA: Open Foundations for Computer-Use AgentsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
SMA: Who Said That? Auditing Membership Leakage in Semi-Black-box RAG ControllingRetrieval-augmented generation → Privacy and security of RAG +1
Bridging Formal Language with Chain-of-Thought Reasoning to Geometry Problem SolvingLLM reasoning → Spatial and embodied reasoning +1
Link Prediction for Event Logs in the Process IndustryRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
Addressing Bias in VLMs for Glaucoma Detection Without Protected Attribute SupervisionMultimodal LLMs / vision-language models → Medical vision-language models
CPO: Addressing Reward Ambiguity in Role-playing Dialogue via Comparative Policy OptimizationLLM reasoning → Reasoning benchmarks and evaluation +2
READER: Retrieval-Assisted Drafter for Efficient LLM InferenceEfficient LLM inference and serving → Speculative decoding
GeoVLA: Empowering 3D Representations in Vision-Language-Action ModelsVision-language-action models → 3D and spatial-aware VLA
VLM-3D:End-to-End Vision-Language Models for Open-World 3D PerceptionMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
MVISU-Bench: Benchmarking Mobile Agents for Real-World Tasks by Multi-App, Vague, Interactive, Single-App and Unethical InstructionsLLM reasoning → Multimodal reasoning +2
Spatial Traces: Enhancing VLA Models with Spatial-Temporal UnderstandingVision-language-action models → 3D and spatial-aware VLA
Activation Steering for Bias Mitigation: An Interpretable Approach to Safer LLMsMechanistic interpretability → Probing deception, bias and beliefs
A Survey on Training-free Alignment of Large Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Retrospective Sparse Attention for Efficient Long-Context GenerationEfficient LLM inference and serving → KV cache optimization
Intrinsic Memory Agents: Heterogeneous Multi-Agent LLM Systems through Structured Contextual MemoryLLM agents and tool use → Agent memory systems
Rethinking Prospect Theory for LLMs: Revealing the Instability of Decision-Making under Epistemic UncertaintyLLM reasoning → Reasoning benchmarks and evaluation
KFFocus: Highlighting Keyframes for Enhanced Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
Rational Inverse Reasoning: Few-Shot Imitation by Inferring Intent through PlanningLLM reasoning → Spatial and embodied reasoning
TaoCache: Structure-Maintained Video Generation AccelerationDiffusion models → Video generation
Lay2Story: Extending Diffusion Transformers for Layout-Togglable Story GenerationDiffusion models → Image generation, text-to-image and editing
Train Long, Think Short: Curriculum Learning for Efficient ReasoningLLM reasoning → Test-time compute and efficient thinking
Reveal-Bangla: A Dataset for Cross-Lingual Multi-Step Reasoning EvaluationLLM reasoning → Reasoning benchmarks and evaluation
Safe Semantics, Unsafe Interpretations: Tackling Implicit Reasoning Safety in Large Vision-Language ModelsLLM reasoning → Reasoning for agents, planning and code +1
Compass-Thinker-7B Technical ReportLLM reasoning → Reinforcement learning for reasoning
ASPD: Unlocking Adaptive Serial-Parallel Decoding by Exploring Intrinsic Parallelism in LLMsEfficient LLM inference and serving → Speculative decoding
CulTrace: Tracing Internal Cultural Reasoning in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation +1
Oblivionis: A Lightweight Learning and Unlearning Framework for Federated Large Language ModelsLLM safety and security → Federated unlearning and poisoning
An Investigation of Robustness of LLMs in Mathematical Reasoning: Benchmarking with Mathematically-Equivalent Transformation of Advanced Mathematical ProblemsLLM reasoning → Mathematical reasoning
Wavelet Mixture of Experts for Time Series ForecastingMixture-of-experts → MoE for time series and graphs
3DFroMLLM: 3D Prototype Generation only from Pretrained Multimodal LLMsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Efficient Agent: Optimizing Planning Capability for Multimodal Retrieval Augmented GenerationMultimodal LLMs / vision-language models → Document understanding and multimodal RAG +2
TARA: Token-Aware LoRA for Composable Personalization in Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build EnvironmentsLLM agents and tool use → Reinforcement learning for LLM agents
Privacy-protected Retrieval-Augmented Generation for Knowledge Graph Question AnsweringRetrieval-augmented generation → Privacy and security of RAG
Designing Memory-Augmented AR Agents for Spatiotemporal Reasoning in Personalized Task AssistanceLLM reasoning → Spatial and embodied reasoning +2
CARES: Collaborative Agentic Reasoning for Error Detection in SurgeryLLM agents and tool use → Medical and scientific domain agents
DevNous: An LLM-Based Multi-Agent System for Grounding IT Project Management in Unstructured ConversationLLM agents and tool use → General LLM agent frameworks and benchmarks
Exploring Palette based Color Guidance in Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
Interpretable Reward Model via Sparse AutoencoderLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
Boosting Action-Information via a Variational Bottleneck on Unlabelled Robot VideosOffline RL and imitation learning from data → Robot manipulation imitation learning
SciRerankBench: Benchmarking Rerankers Towards Scientific Retrieval-Augmented Generated LLMsRetrieval-augmented generation → Agentic RAG, agents and memory
Elucidating Rectified Flow with Deterministic Sampler: Polynomial Discretization Complexity for Multi and One-step ModelsDiffusion models → Flow matching, time series and science
Simulating Generative Social Agents via Theory-Informed Workflow DesignLLM reasoning → Reasoning for agents, planning and code +1
Generative Modeling for Robust Deep Reinforcement Learning on the Traveling Salesman ProblemDeep reinforcement learning methods → RL for games and combinatorial optimization
A Survey on Parallel Text Generation: From Parallel Decoding to Diffusion Language ModelsDiffusion models → Discrete and text diffusion +1
CRADLE: Conversational RTL Design Space Exploration with LLM-based Multi-Agent SystemsLLM agents and tool use → Software engineering coding agents
Towards Safe Imitation Learning via Potential Field-Guided Flow MatchingDiffusion models → Diffusion and flow policies for robotics +1
OmniVTLA: Vision-Tactile-Language-Action Models with Semantic-Aligned Tactile SensingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
DiffVolume: Diffusion Models for Volume Generation in Limit Order BooksDiffusion models → Flow matching, time series and science
STELAR-VISION: Self-Topology-Aware Efficient Learning for Aligned Reasoning in VisionLLM reasoning → Multimodal reasoning +1
Expert-Guided Diffusion Planner for Auto-BiddingDiffusion models → Diffusion and flow policies for robotics
Exploring Large Language Model Agents for Piloting Social ExperimentsLLM agents and tool use → Social simulation and multi-agent debate
Convergent Q-Learning for Infinite-Horizon General-Sum Markov Games through Behavioral EconomicsDeep reinforcement learning methods → RL for games and combinatorial optimization
Aryabhata: An exam-focused language model for JEE MathLLM reasoning → Mathematical reasoning
Quick on the Uptake: Eliciting Implicit Intents from Human Demonstrations for Personalized Mobile-Use AgentsLLM agents and tool use → GUI and mobile agents
AME: Aligned Manifold Entropy for Robust Vision-Language DistillationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
MiGrATe: Mixed-Policy GRPO for Adaptation at Test-TimeLLM reasoning → Reinforcement learning for reasoning
InternBootcamp: Boosting LLM Reasoning with Verifiable Task ScalingLLM reasoning → Reinforcement learning for reasoning
AgriGPT: a Large Language Model Ecosystem for AgricultureRetrieval-augmented generation → Time series and agricultural RAG
Securing Educational LLMs: A Generalised Taxonomy of Attacks on LLMs and DREAD Risk AssessmentLLM safety and security → Prompt injection and agent security
Optimizing Retrieval-Augmented Generation (RAG) for Colloquial Cantonese: A LoRA-Based Systematic ReviewRetrieval-augmented generation → RAG pipeline design and evaluation
Transferable Model-agnostic Vision-Language Model Adaptation for Efficient Weak-to-Strong GeneralizationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
DocThinker: Explainable Multimodal Large Language Models with Rule-based Reinforcement Learning for Document UnderstandingLLM reasoning → Multimodal reasoning +1
DeepFleet: Multi-Agent Foundation Models for Mobile RobotsLLM agents and tool use → Multimodal and embodied agents
Superclass-Guided Representation Disentanglement for Spurious Correlation MitigationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Unlocking the Potential of Diffusion Priors in Blind Face RestorationDiffusion models → Inverse problems and image restoration
Fine-grained Video Dubbing Duration Alignment with Segment Supervised Preference OptimizationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment

All 355