mlsanityData to 7 Oct 2026

Papers

New on arXiv

Sat 13 Jun 2026

219 papers

  1. Statutory AI: Aligning Large Language Models With Legal NormsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment +1
  2. Director: Accelerating Distributed MoE Serving via Online Proactive Expert PlacementMixture-of-experts → Efficient MoE training and inference systems
  3. Reward Transport: Property Control in Flow Matching via Noise-Space AlignmentDiffusion models → Flow matching, time series and science +1
  4. Thinking Out Loud: Real-Time Deception Monitoring in Asymmetric LLM NegotiationsLLM agents and tool use → Financial trading and forecasting agents
  5. ConCise: Training-Free Conclusion-Chain State Compression for Cost-Efficient Multi-Step RAG ServicesRetrieval-augmented generation → Generation and context integration
  6. MemoryVAM: Integrating Memory into Video Action Model for Robot ManipulationWorld models → Embodied and robot world models
  7. ClayBuddy: A Framework, Evaluation, & Mitigation of Coding Agent FailuresLLM agents and tool use → Software engineering coding agents
  8. Stochastic Thermodynamics and SDE-based Generative ModelsDiffusion models → Diffusion foundations and sampling
  9. Securing Multi-Agent GIS Systems: Risk Evaluation and Prompt Hardening OptimizationLLM agents and tool use → Agent threats, guardrails and governance
  10. Reinforcement Learning-Guided Retrieval with Soft Fusion for Robust Multimodal Imitation Learning under Missing ModalitiesOffline RL and imitation learning from data → Robot manipulation imitation learning
  11. ToolMenuBench: Benchmarking Tool-Menu Filtering Strategies for Reliable and Efficient LLM AgentsLLM agents and tool use → Tool learning and function calling
  12. Frame-Conditioned Moral Computation in LLaMA 3.1-8B-Instruct: A Mechanistic Interpretability Audit of Ethical ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  13. The Perils of Agency: How Developers Perceive, Prioritize, and Address Risks in Agentic AI ProductsLLM agents and tool use → Software engineering coding agents
  14. Ricci-Filtration: Boosting Retrieval-Augmented Generation Reranker to Query-Answer Tasks by Discrete Ricci FlowRetrieval-augmented generation → Generation and context integration +1
  15. Lesion-DDPM: Lesion-Enhanced 3D Diffusion for MS MRI SynthesisDiffusion models → Medical imaging and segmentation
  16. Understanding Diversity Collapse in RLVR via the Lens of OvertrainingLLM reasoning → Reinforcement learning for reasoning
  17. A Spatio-Temporal Expert Prefetching Framework for Efficient MoE-based LLM InferenceMixture-of-experts → Efficient MoE training and inference systems
  18. PHINN: Persistent Homology Inspired Neural Network for Rare-Event Time Series GenerationDiffusion models → Flow matching, time series and science
  19. Defending against Adaptive Prompt Injection Attacks via Reasoning-enabled Task AlignmentLLM reasoning → Reasoning for agents, planning and code +2
  20. Post-Launch Capability Expansion of Vision-Language Models via Prompting for On-Orbit Spacecraft InspectionMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  21. Pepti-Agent: An AI Agent for Peptide Design and OptimizationLLM agents and tool use → Medical and scientific domain agents
  22. Let LLMs Judge Each Other: Multi-Agent Peer-Reviewed Reasoning for Medical Question AnsweringLLM reasoning → Clinical and biomedical applications +1
  23. From Frames to Temporal Graphs: In-Context Egocentric Action Recognition with Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  24. CHILLGuard: Towards Fine-Grained Chinese LLM Safety Guardrail with Scalable Data Construction and Model-aware Preference AlignmentLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  25. Not All Skills Help: Measuring and Repairing Agent KnowledgeLLM agents and tool use → Agent skill learning and evolution
  26. Timestep Rescheduling in Diffusion InversionDiffusion models → Inverse problems and image restoration
  27. Reward Hacking in Language Model Agents: Revisiting AI Safety GridworldsLLM agents and tool use → Agent threats, guardrails and governance +1
  28. Rethinking the Role of Efficient Attention in Hybrid ArchitecturesLLM reasoning → Test-time compute and efficient thinking
  29. CoAgent: Concurrency Control for Multi-Agent SystemsLLM agents and tool use → Software engineering coding agents
  30. S1-DeepResearch: Beyond Search, Toward Real-World Long-Horizon Research AgentsLLM agents and tool use → Web, search, and research agents
  31. APEX: Adaptive Principle EXtraction A Three-Layer Self-Evolution Framework for Production AI AgentsLLM agents and tool use → Software engineering coding agents
  32. DiRecT: Safe Diffusion-Based Planning via Receding-Horizon DenoisingDiffusion models → Diffusion and flow policies for robotics
  33. Beyond Monolingual Deep Research: Evaluating Agents and Retrievers with Cross-Lingual BrowseComp-PlusLLM agents and tool use → Web, search, and research agents
  34. CausalDrive: Real-time Causal World Models for Autonomous DrivingWorld models → World models for autonomous driving +1
  35. Replay What Matters: Off-Policy Replay for Efficient LLM Reinforcement UnlearningLLM safety and security → Machine unlearning
  36. HoloRec: Holistic Encoding and Interleaved Reasoning for Generative RecommendationLLM reasoning → LLM reasoning for recommendation
  37. Semantic DLM+: Improving Diffusion Language Models through Bias-variance Trade-off in Transition Kernel DesignDiffusion models → Discrete and text diffusion
  38. PPDM: Pixel Puzzling Diffusion Model for Speed and Memory Efficient Volumetric Medical Image TranslationDiffusion models → Medical imaging and segmentation
  39. Conditional Multi-Event Temporal Grounding in Long-Form VideoMultimodal LLMs / vision-language models → Video understanding with MLLMs
  40. Forced Deferral: Manipulating Routing Decisions in Multimodal LLM CascadesLLM reasoning → Reasoning for agents, planning and code +1
  41. Adapting Reinforcement Learning with Chain-of-Thought Supervision for Explainable Detection of Hateful and Propagandistic MemesLLM reasoning → Reasoning benchmarks and evaluation
  42. LatentGym: A Testbed For Cross-Task Experiential Learning With Controllable Latent StructureLLM agents and tool use → Agent skill learning and evolution
  43. HemExp: Clinically-Guided Latent Diffusion for Modeling Hematoma ExpansionDiffusion models → Medical imaging and segmentation
  44. A Formal Framework for Declarative Agentic AI in Business Process AnalysisLLM agents and tool use → Software engineering coding agents
  45. Acting While Understanding: Asynchronous Semantic-Action Decoupling for Real-Time Vision-Language-Action ModelsVision-language-action models → Efficient VLA inference and adaptation
  46. AI-driven Software Development: A Pragmatic Path to Agentic Development ProcessesLLM agents and tool use → Software engineering coding agents
  47. MamBOA: State-Space Architecture for Video RecognitionState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  48. Trust-Region Diffusion Policies for Massively Parallel On-Policy RLDiffusion models → Diffusion and flow policies for robotics
  49. Benign in Isolation, Harmful in Composition: Security Risks in Agent Skill EcosystemsLLM agents and tool use → Agent threats, guardrails and governance
  50. Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space DiffusionDiffusion models → Diffusion foundations and sampling
  51. Rethinking Implicit Spatial Representation in Visuomotor Policy LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
  52. Visual-Seeker: Towards Visual-Native Multimodal Agentic Search via Active Visual ReasoningLLM reasoning → Multimodal reasoning +2
  53. Edu-Theater: A Data-Efficient Agent Framework for Scalable Learner Behavior Simulation through Staging Roll-CallLLM agents and tool use → Educational agents and math problem solving
  54. Comparing Human Gaze and Vision-Language Model Attention in Safety-Relevant EnvironmentsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  55. Keep It in Mind: User Centric Continual Spatial Intelligence Reasoning in Egocentric Video StreamsLLM reasoning → Spatial and embodied reasoning
  56. Adaptive Inference-Time Scaling via Early-Step Latent Verification for Image EditingLLM reasoning → Multimodal reasoning
  57. CONCORD: Asynchronous Sparse Aggregation for Device-Cloud RAG under Document IsolationRetrieval-augmented generation → Privacy and security of RAG
  58. Coordinated Scheduling for MoE LLM ServingMixture-of-experts → Efficient MoE training and inference systems +1
  59. Label Shift Aware Adaptation for Online Zero-shot Learning with Contrastive Language-Image Pre-Training (CLIP)Multimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  60. VLALeaks: Membership Inference Attacks against Vision-Language-Action ModelsVision-language-action models → Safety and adversarial attacks +1
  61. GeoStream: Toward Precise Camera Controlled Streaming Video GenerationWorld models → Video-generation world models and simulators
  62. DLWM: Diverse Latent World Models for Efficient Multimodal ReasoningWorld models → World models for language agents +2
  63. Exploring a Layer-Wise Design Space for KV Cache EvictionEfficient LLM inference and serving → KV cache optimization
  64. Can Agents Read the Room? Benchmarking Visual Social Intelligence in Multimodal SimulationLLM agents and tool use → Multimodal and embodied agents
  65. EChO-Agent: Evidence Chain Orchestration Agent for Audio ReasoningLLM reasoning → Audio-language model reasoning
  66. Beyond Accuracy: Measuring Bias Acknowledgment in Chain-of-Thought Reasoning for Responsible AI EvaluationLLM reasoning → Prompting and chain-of-thought reasoning
  67. Towards Verifiable Agentic Data Science: Solving Irregular TSQA Via Tool-Grounded ReasoningLLM reasoning → Time series reasoning +1
  68. Think Less, Act Early: Reinforced Latent Reasoning with Early Exit in Vision-Language-Action ModelsLLM reasoning → Spatial and embodied reasoning +2
  69. AdaMame: A Training Recipe for Adaptive Multilingual ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  70. Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter ScaleLLM reasoning → Reasoning for agents, planning and code +1
  71. Risk-Aware LLM Agents for Geospatial Data Retrieval: Design and Preliminary Adversarial EvaluationLLM agents and tool use → Multimodal and embodied agents +1
  72. Stop When Further Reasoning Won't Help: Attention-State Adaptive Generation in Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
  73. AutoDojo: Adaptive Black-Box Attacks Reveal the Limits of IPI Defenses and Task-Specification Effects in LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  74. Temporal Difference Learning for Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  75. OSGuard: A Benchmark for Safety in Computer-Use AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  76. How Should World Models Be Evaluated for Embodied Decision-Making? A Decision-Making-Centric PositionWorld models → World models for navigation
  77. Beyond Raw Transcripts: Structured Persona Extraction for LLM-Based Digital Twins
  78. Bankruptcy Prediction via Hybrid Resampling and Stacking Ensemble Techniques with Explainable Artificial Intelligence (XAI)-Driven Analysis
  79. Beyond Tracking or Shortcut: Composition-Bounded Predictive States in Poker Autoregressive Models
  80. Beyond Backbone Backpropagation: A Decoupled Strategy for Efficient Transfer Learning
  81. Automatic Differentiation from Scratch: How PyTorch Computes Gradients in Physics-Informed Neural Networks
  82. TAKE: Trajectory-Aware Knowledge Estimation for Text Dataset Distillation
  83. ECG-LDC: A Hardware-Efficient Low-Dimensional Computing Framework for ECG Arrhythmia Classification
  84. Accelerating GPU Inference of Large Language Models with Moderately Unstructured Sparse Weight Matrices
  85. DaDaDa: A Dataset for Data Pricing in Data Marketplaces
  86. HERO: A Heterogeneity-Aware Benchmark Library for Federated Continual Learning
  87. LieBN: Batch Normalization over Lie Groups
  88. A UAV-Based Multi-Modal Vision System for Automated Sideslope Deformation Monitoring and Hazard Detection
  89. Beyond ROC-AUC: Operating-Point Performance Reporting for Biometric Verification
  90. Diagnosing Shape-Prior Shortcuts in Long-Range Single-Shot Fringe Projection Profilometry
  91. Towards Data-Efficient Cross-Device Generalization of Grad-Shafranov Equilibria via Transfer Learning Neural Operator
  92. AthDGC: An Open Diachronic Greek Treebank with Indo-European Parallels
  93. LLM4RTL: Tool-Assisted LLM for RTL Generation
  94. Model Stealing Through the Lens of Model Multiplicity
  95. ST-DiffEye: Diffusion-based Continuous Gaze Generation via Joint Scanpath-Trajectory Modeling
  96. Evaluative Judgement in Teaching AI-based Translation: A Class-room Case Study of AI-Mediated Translation and Post-Editing
  97. Bayesian 3D Steerable CNNs: Enabling Equivariance and Uncertainty Quantification Simultaneously
  98. Who Drifted: the System or the Judge? Anytime-Valid Attribution in LLM Evaluation Pipelines
  99. Analyzing Visual Aircraft Representations with Sparse Autoencoders
  100. ESBMC-PLC: Formal Verification of IEC 61131-3 Ladder Diagram Programs Using SMT-Based Model Checking
All 219
  1. Structured Nonparametric Variational Inference for Dependent Latent Modeling
  2. Transfer Learning for FHIR Questionnaire Terminology Binding
  3. Hierarchical Modeling of ICD Codes in EHR Foundation Models
  4. A Conservation Law for Equilibrium Propagation and Coupled Learning
  5. Coercivity and Local Convergence of Physical Learning in Linear Circuits
  6. The Reverse Telescoping Coordinate System for Positive Definite Matrices: Geometry, Computation, and Generative Modeling
  7. Beyond Classification: A Cough Regression Benchmark for Respiratory Acoustic Foundation Models
  8. Constitutional Value Potentials: reading and steering internal priority margins in language models
  9. Encode Errors: Representational Retrieval of In-Context Demonstrations for Multilingual Grammatical Error Correction
  10. Few-Shot Biomedical Relation Extraction with Large Language Models: A Viable Alternative to Supervised Learning?
  11. Segmentation-based Detection for Efficient Multi-Task Spacecraft Perception
  12. T-Mem: Memory That Anticipates, Not Archives
  13. Finite Resources False Discovery Rate Control in Structured Hypothesis Spaces
  14. A Compositional Framework for Open-ended Intelligence
  15. Learning Earthquake Wave Arrival Time Picking from Labels with Inaccuracies
  16. MNet++: Extended 2D/3D Networks for Anisotropic Medical Image Segmentation
  17. Repeated Bilateral Trade: The Quest for Fairness
  18. Cognitive Trajectory Modeling: Quantifying Human-AI Co-Creation through Cognitively Grounded Interaction Trajectories
  19. ShipNet: A Geometric Deep Learning Surrogate for Real-Time Ship Hydrodynamics
  20. Sustainable Face Recognition on Low-Power Devices with VQ-VAE Embeddings
  21. Chroma-gated, differentiable OKLCH interpolation: Continuous Oklab fallback for color-cast reduction
  22. Facial Affect Analysis for Service-Oriented Systems: Advances, Challenges, and Future Visions
  23. LearnOpt: Recovering the Latent Cognitive Structure of Standardized Examinations via Knowledge Graphs and Constrained Optimization
  24. Intrinsic Computational Functionalism and Simulated Consciousness
  25. DYNA-PRUNER: Input-Adaptive Data-Model Co-Pruning for Efficient and Scalable Spatio-Temporal Media Prediction
  26. Generative modelling powered by room-temperature polariton condensates
  27. Privacy-Preserving Text Sanitization for Distributed Agents Collaboration via Disentangled Representations
  28. Probabilistic Signature Inversion: Learning Conditional Distributions from Truncated Signatures
  29. SGFormer++: Semantic Graph Transformer for Incremental 3D Scene Graph Generation
  30. Prior over Evidence: Stereotype-Driven Diagnosis in LLM-Based L2 Pronunciation Feedback
  31. ChatPlanner: A Large Language Model Framework for Personalized Public Transit Routing
  32. LLMs on Tabular Data with Limited Semantics: Evidence from Industrial Car Retrofit Prediction
  33. CoMNet: A MedNeXt-CorrDiff Framework for Multi-Site Brain Tumor Segmentation
  34. Discovering Lattice Reduction Strategies via Self-Play
  35. CODA-BENCH: Can Code Agents Handle Data-Intensive Tasks?
  36. Hybrid NARX-LLM for Greenland Iceberg Discharge: Prompt-Driven Residual Correction
  37. G2IA: Geometry-Guided Instance-Aware Retrieval and Refinement for Cross-Modal Place Recognition
  38. Decoupled Motion Representation Learning for Moving Infrared Small Target Detection
  39. CAP: Towards PPG Universal Representation Learning with Patient-level Supervision
  40. Enhancing Precision Agriculture with a Hybrid Deep Learning Framework for Multi-Class Plant Disease Classification and Interpretability
  41. Rethinking Structural Anomaly Detection: From Decision Boundaries to Projection Operators
  42. RECTOR: Masked Region-Channel-Temporal Modeling for Affective and Cognitive Representation Learning
  43. Improving Federated Graph Recommendation with Semantic Guidance
  44. Feature Attribution in Directed Acyclic Graphs Using Edge Intervention
  45. Dual-Network PINNs for Optimal Control: A Reproducible Benchmark on the Mass-Spring-Damper System
  46. When to use what Schatten-p norm in deep learning?
  47. Evaluating and Preserving Lexical Stress in English-to-Chinese Speech-to-Speech Translation
  48. Trusted Multi-View Deep Learning Classification of Fetal Congenital Heart Disease with Feature-level and Decision-level Fusion
  49. Mask-Proof: An LLM-based Automated Data Curation Pipeline on Mathematical Proofs
  50. AI for Social Good: An Investigation of the Causal Relationship Between Environmental Regulations and Their Effects on Air Pollution in London, UK
  51. Focus, Align, and Sustain: Counteracting Gradient Dilution in Incremental Object Detection
  52. Driving, Fast or Slow? Neuro-Symbolic Guidance for Motion Prediction in Multi-Modal Ground Mobility
  53. Landmark-free Assessment of Lower-limb Alignment with Implicit Neural Shape Functions from Knee Radiographs
  54. Exploring Starts Are Not Enough: Counterexamples and a Fix for Monte Carlo Exploring Starts
  55. Provenance-Enhanced Statements in Knowledge Graphs
  56. M-CTX: Exact and Scalable Spatial Context Retrieval for Trajectory Analytics
  57. SPARK: Spatial Policy-driven Adaptive Reinforcement learning for Knowledge distillation
  58. EnvShip: A Unified Framework for Context-Aware and Cross-Region Vessel Trajectory Forecasting
  59. HairLRM: Strand-based Hair Modeling via Large Reconstruction Models
  60. Optimized Sequential Testing for Binary Ensemble Classifiers
  61. Surrogate-Assisted Framework for SI-Compliant Interconnect Design Optimization Using the Earth Mover's Distance
  62. Can Neural Networks Achieve Optimal Computational-statistical Tradeoff? An Analysis on Single-Index Model
  63. Conformal Candidate Certification for Offline Model-Based Optimization
  64. Spokes: Optimizing for Diverse Pretraining Data Selection
  65. Quantum-classical hybrid models based on error correction for time series forecasting
  66. Attribute Inference from Interactive Targeted Ads
  67. Controlled Dynamics Attractor Transformer
  68. AI Contagion in Social Networks
  69. A Koopman-PINN Framework for Epidemic Models: Parameter Inference and Forecasting
  70. CogGuard: Cognitive and Operational Profiling for Proactive Warning in Edge Intelligent Services
  71. City landscape in sight: A crowdsourced framework for unlocking urban-scale window view perceptions from real estate imagery
  72. StarOR: Synergizing Tree Search and Test-Time Reinforcement Learning for Optimization Modeling
  73. AmchiBias: Measuring Stereotypical Bias in Goan Identity Groups with a Minimal Pair Dataset in English and Konkani
  74. FreeSonic: Training-Free Temporal-Aware Decoupled Attention for Precise Audio Editing
  75. Enabling Real-Time Point-of-Care Ultrasound Segmentation: A GPU-Free Deployment in Resource-Limited Settings
  76. Towards a Unified Generative Model for Scarce Time Series with Domain Experts
  77. Variational Network with Wavelet-based UNET in Accelerated MRI Reconstruction from Under Sampled K-space Data
  78. Beyond Layer Importance in Layer-wise Sparsity: An Inter-Layer Perturbation-Absorption Perspective
  79. RefGC-SR2: Reference-guided Super-Resolution and Refinement of AI Generated Content
  80. Semantic Reasoning in Medicine: The Role of Knowledge Graphs Across Five Key Domains
  81. False Sense of Safety in Selective Signal Classification: Auditing Bound Tightness and Exchangeability for Risk Control
  82. HiRo: A Compact Four-Directional Hierarchical Reservoir Token-Mixer for Efficient Image Classification
  83. MimicIK: Real-Time Generative Inverse Kinematics from Teleoperation with FK Consistency
  84. Contextual Bandits for Maximizing Stimulated Word-of-Mouth Rewards
  85. PACUTE: Phonology-, Affix-, and Character-level Understanding of Tokens for Filipino
  86. MotionVLA: Vision-Language-Action Model for Humanoid Motion
  87. Beyond Scalar Distances: Semantic Attribute Gradients from Frozen MLLMs for Visual Embeddings
  88. DragMesh-2: Physically Plausible Dexterous Hand-Object Interaction with Articulated Objects
  89. EyeMVP: OCT-Informed Fundus Representation Learning via Paired CFP--OCT Pretraining
  90. Data-Centric Benchmarking of Exploit Generation in LLMs: Understanding the Impact of Fine-Tuning
  91. When Cognitive Graphs Meet LLMs: BDEI Cognitive Pathways for Panic Emotional Arousal Prediction
  92. Multi-view feature High-order Fusion for Space Weak Object Detection and Segmentation
  93. Teacher-Student Structure for Domain Adaptation in Ensemble Audio-Visual Video Deepfake Detection
  94. Diversity-Driven Offline Multi-Objective Optimization via Nested Pareto Set Learning
  95. Learn Temporal Consistency For Robust Satellite Video Detector
  96. Physics-Driven Zero-Shot MRI Reconstruction with Non-local Image Priors
  97. Text-Driven Fusion for Infrared and Visible Images: Achieving Image Scene Adaptation on Hyperbolic Space
  98. VGPT-RSI for RH-Adjacent Formal Progress: Boundary Certificates, Verified Finite Lagarias Inequalities, and Explicit Failure Localization
  99. High-Dimensional Random Projection for Activation Steering in Language Models
  100. Sensory Restoration via Brain-Computer Interfaces: A Scoping Review
  101. When the Same Musical Knowledge Forgets Differently: A Clean Probe of Pathway-Dependent Forgetting
  102. An Integrable Token Mixing Layer from the Generalized Yang Baxter Equation
  103. Cognitive Debt: AI as Intellectual Leverage and the Dynamics of Systemic Fragility
  104. TriAdReview: Triangular Adversarial Review Architecture for Multi-Model Technical Document Generation
  105. Texture-Shape Bias Balancing for Robust Synthetic-to-Real Semantic Segmentation in Automotive NIR Imagery
  106. CoCoGEC: Counterfactual Generation for Robust Grammatical Error Correction
  107. Phase-Localized Curation Does Not Help: A Negative Result on Per-Phase Metric Selection for Demonstration Filtering
  108. A Practical Evaluation Method for Long-Form Simultaneous Speech-to-Speech Translation
  109. Machine Learning and the Random Walk Puzzle: Forecasting the CAD/USD Exchange Rate with Expanding Window Evaluation and SHAP Interpretability
  110. Bridging Geographic Bias in Urban Streetscape Inference via Lifelong Learning with Visual-Semantic Pivoting
  111. Size Doesn't Matter: Cosine-Scored Sparse Autoencoders
  112. Physics-conforming Latent Twins
  113. PANDA: An LLM-Enhanced Performance-Driven Analog Design Framework Bridging Design Intent and Layout Generation
  114. Gaussian Spatial Priors for Anatomy-Aware Object Detection in Surgical Videos
  115. Equity with Efficiency: An Empirical Study of Tokenizers for Multilingual Large Language Models
  116. Fusion is not one-size-fits-all: Cross-Modal Representation Alignment for Time-to-Event Modeling
  117. ReportQA: QA-Based Radiology Report Evaluation
  118. Transformers Learn the Mestre-Nagao Heuristic
  119. Cloze: An Open Research Platform for Studying Human-AI Conversations in Mental Health Contexts