Entities · Products
alphaXiv
317 articles tagged with this entity.
-
Think Big, Search Small: Where Capacity Matters in Hierarchical Search Agents?
-
The Appeal and Reality of Recycling LoRAs with Adaptive Merging
-
Infinite Worlds with Versatile Interactions
-
Reason Less, Verify More: Deterministic Gates Recover a Silent Policy-Violation Failure Mode in Tool-Using LLM Agents
-
Can Trustless Agents Be Trusted? An Empirical Study of the ERC-8004 Decentralized AI Agent Ecosystem
-
Predicting LLM Safety Before Release by Simulating Deployment
-
AirPASS: Over-the-Air Federated Learning via Pinching Antenna Systems
-
From Content to Audience: A Multimodal Annotation Framework for Broadcast Television Analytics
-
Monitoring Transformative Technological Convergence Through LLM-Extracted Semantic Entity Triple Graphs
-
Reasoning Consistency Scanning: A Framework for Auditing Chain-of-Thought Validity in AI Safety Evaluations
-
WildCity: A Real-World City-Scale Testbed for Rendering, Simulation, and Spatial Intelligence
-
Specification Grounding Drives Test Effectiveness for LLM Code
-
DASH: Dynamic Audio-Driven Semantic Chunking for Efficient Omnimodal Token Compression
-
VASP Agent: An Agentic Framework for Autonomous First-principles Calculations
-
Beyond Static Evaluation: Building Simulation Environments for Scalable Agentic Reinforcement Learning
-
RMISC: A Large-scale Real-world Multivariate Corpus for Time Series Foundation Models
-
Narrative-Centered Emotional Reflection: An Early Prototype for AI-Supported Emotional Self-Reflection
-
Multi-Task Instruction Tuning via Data Scheduling for Low-Resource Arabic SpeechLLMs
-
Channel-wise Retrieval for Multivariate Time Series Forecasting
-
Polyglot Teachers: Evaluating Language Models for Multilingual Synthetic Data Generation
-
ROK-FORTRESS: Measuring the Effect of Geopolitical Transcreation for National Security and Public Safety
-
Enhancement of E-commerce Sponsored Search Relevancy with LLM
-
Don't Wait to Reply: Towards Responsive yet Thoughtful Dialogue through Proactive Thinking
-
TAMA: A Human-AI Collaborative Thematic Analysis Framework Using Multi-Agent LLMs for Clinical Interviews
-
Knowledge-Centric Information Systems
-
A Reliable Context-Aware and Temporal Planning Framework for Autonomous Driving
-
Programming over Thinking: Efficient and Robust Multi-Constraint Planning
-
Re:Form -- Reducing Human Annotations in Scalable Formal Software Verification with RL in LLMs: A Preliminary Study on Dafny
-
Metronome: Bound the Cache, Keep the Beat for Real-Time Interaction Model Serving
-
Vision Token Manipulation Attacks on Cloud-Edge Inference of Large Vision-Language Models
-
OpenGlass: A Sensing-Computing Split Architecture for Local MLLM-Driven Real-Time Visual Assistance
-
Builder, Defender, Breaker: The Case Against Removing the Human from the AI-Driven Security Lifecycle
-
Efficient Discovery of Conditional Dependencies with Desbordante
-
How Much is Left? LLMs Linearly Encode Their Remaining Output Length
-
A Fair Benchmarking of Deep Relational Database Learning Models
-
Last-Meter Precision Navigation for UAVs: A Diffusion-Refined Aerial Visual Servoing Approach
-
An Exploration of Agentic Information Fusion for Test Maintenance Prediction
-
When Simpler Is Better: Evaluating Translation Pipelines for Medieval Latin Manuscripts
-
AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments
-
Toward Trustworthy Large Language Model Agents in Healthcare
-
PraMem: Practice-derived Experiential Memory for Long-horizon Behavior Prediction
-
DC-Motion: Decoupling Structure and Details via Discrete-Continuous Tokens for Human Motion Generation
-
MIRAGE: Defending Long-Form RAG Against Misinformation Pollution
-
Human-Centric Reflective Architecture for Human-AI Collaborative Decision-Making
-
SPORK: Self-Speculative Forking to Accelerate Agentic LLM Inference
-
Efficient Decentralized Multi-task Dataset Valuation via Model Merging
-
Transplanting, inverting, and preventing a misalignment persona: method-conditional emergent misalignment in Qwen2.5
-
What is Left for Us? Second Scholarship Against the Degradation of Research by AI
-
HCSU: A Dataset and Benchmark for Fine-Grained Historical Calligraphy Style Understanding
-
AOI: Context-Aware Multi-Agent Operations via Dynamic Scheduling and Hierarchical Memory Compression
-
DualView: Preventing Indirect Prompt Injection in Personal AI Agents
-
PLACEMEM: Toward a Compute-Aware Memory Plane for Lifelong Agents
-
CausalGame: Benchmarking Causal Thinking of LLM Agents in Games
-
Adaptive Batch Sizes Using Non-Euclidean Gradient Noise Scales for Stochastic Sign and Spectral Descent
-
Agent4cs: A Multi-agent System for Code Summarization in Large Hierarchical Codebases
-
TCG-AR: Real-Time Multi-View Augmented Reality for Trading Card Game Streaming
-
BRIDGE: Predicting Human Task Completion Time From Model Performance
-
SINA: A Fully Automated Circuit Schematic Image to Netlist Generator Using Artificial Intelligence
-
Atomic Task Graph: A Unified Framework for Agentic Planning and Execution
-
The Eticas AI Risk Taxonomy: Open Infrastructure for Operationalizing AI Audits
-
Beyond Supervised Clarification: Input Rewriting with LLMs for Dialogue Discourse Parsing
-
EPC: A Standardized Protocol for Measuring Evaluator Preference Dynamics in LLM Agent Systems
-
Clinician-Level Agreement Without Clinical Caution: LLM Evaluator Limits in Medical AI Benchmarking
-
Vertigo Vertigo: Reconstructing a Cinematic Ideal through its Predictive AI Double
-
CogTax: A Four-Level Cognitive Taxonomy for Command-Line Computing Education
-
BaRA: BFS-and-Reflection Web Data Collection Agent
-
Large language model-enabled automated data extraction for concrete materials informatics
-
Multi-Turn Agentic Scientific Literature Search via Workflow Induction
-
A Text-Steerable Instrument for Sketching Procedural Soundscapes via Language Models
-
FLARE-AI: Flaw Reporting for AI
-
Training Therapeutic Judges and Multi-Agent Systems for Human-Aligned Mental Health Support
-
LeCropFollow: Latent Space Planning for Navigation in Unstructured Crop Fields
-
A Three-Phase Foundation Model for Tax-Aware Personalized Portfolio Management
-
Learning from Failure: Inference-Time Self-Improvement for Computer-Use Agents
-
ReplicatorBench: Benchmarking LLM Agents for Replicability in Social and Behavioral Sciences
-
ORCA: Open-ended Response Correctness Assessment for Audio Question Answering
-
An Agentic AI Pipeline for Appliance-Level Energy Anomaly Detection and LLM-Driven Recommendations
-
Accelerating scientific discovery with Co-Scientist
-
Diagnosing and Mitigating Context Rot in Long-horizon Search
-
Complete virtual unwrapping and reading of a rolled Herculaneum papyrus
-
GarmentZoom: Generating Zoomable Images from Garment Listings
-
HomeDiffusion: Zero-Shot Object Customization with Multi-View Representation Learning for Indoor Scenes
-
LoRA-Tuned Large Language Models for Dementia Detection via Multi-View Speech-Derived Features
-
Labeling Training Data for Entity Matching Using Large Language Models
-
SrDetection: A Self-Referential Framework for Data Leakage Detection in Code Large Language Models
-
LLM Agents Are Latent Context Managers: Eliciting Self-Managed Context via a Proprioceptive Dashboard
-
BackTranslation2.0 -- A Linguistically Motivated Metric to Assess Sign Language Production
-
Neural Procedural Memory: Empowering LLM Agents with Implicit Activation Steering
-
TextClusterLab: An Integrated Framework for Reliable Text Clustering Studies
-
Ensemble Learning Based Classification Algorithm Recommendation
-
Entity Binding Failures in Tool-Augmented Agents
-
AnyBody: Free-Form Whole-Body Humanoid Control from Arbitrary Keypoint Guidance
-
TopoAgent: An Agentic Framework for Automated Topology Learning in Medical Imaging
-
Research Entity Extraction and Topic Detection from UKRI Grant Proposals
-
Depth Exploration for LLM Decoding
-
A Classifier-Agnostic Zero-Shot Adversarial Attack Detection via CLIP
-
Learning to Segment Liquids in Real-world Images
-
SpreadsheetBench 2: Evaluating Agents on End-to-End Business Spreadsheet Workflows
-
Echoes of Human Malice in Agents: Benchmarking LLMs for Multi-Turn Online Harassment Attacks
-
EfficientUICoder: A Bidirectional Token Compression Framework for Efficient MLLM-Based UI Code Generation
-
Diff-Based Code Corruption using LLMs for Large-Scale Bugfix Benchmarking
-
ExACT: Exemplar-Driven Calibrated Refinement for Training-Free Visual Grounding in Remote Sensing Images
-
MARS: A neurosymbolic approach for interpretable drug discovery
-
HiComm: Hierarchical Communication for Multi-agent Reinforcement Learning
-
The Digital Afterlife of Empires: Four Language Models Converge on the Same Imperial Cartography of Writing
-
Can Fine-Tuning Erase Your Edits? On the Fragile Coexistence of Knowledge Editing and Adaptation
-
Argus: Metric Panoramic 3D Reconstruction for Indoor Scenes
-
Categorize Early, Integrate Late: Divergent Processing Strategies in Automatic Speech Recognition
-
DialogPII: A multilingual dataset of synthetic dialog transcripts to detect personal information
-
KrishokChat: A Citation-Grounded Dataset and Benchmark for Bengali Agricultural Advisory
-
DeepTrans Studio: Turning Expert Interventions into Shared Team Knowledge in Agentic Translation Workflows
-
SafePyramid: A Hierarchical Benchmark for In-context Policy Guardrailing
-
Towards Automating Scientific Review with Google's Paper Assistant Tool
-
Auto-Configuring Scientific Simulators with Lightweight Coding-Agent Adapters
-
"Generate" the Future of Work through AI: Empirical Evidence from Online Labor Markets
-
When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Models
-
SpaceDG: Benchmarking Spatial Intelligence under Visual Degradation
-
Multimodal Evaluator Preference Collapse: Cross-Modal Coupling in Self-Evolving Agents
-
On the Effect of Uncertainty on Layer-wise Inference Dynamics
-
SidConArena: An Environment Evaluating Agents in Open-Ended,Positive-Sum Bargaining Game
-
Symmetry-Aware Transformer Training for Automated Planning
-
JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications
-
MultiHashFormer: Hash-based Generative Language Models
-
Agentic Publication Protocol: An Attempt to Modernize Scientific Publication
-
Beyond Logical Forms: LLM-Extracted Patterns for Fallacy Classification
-
Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs
-
RoPEMover: Depth-Aware Object Relocation via Positional Embeddings
-
NaviCache: Test-Time Self-Calibration Caching for Video Generation
-
ProfileFoundry: A Synthetic Person-Object Substrate for Privacy, Memory, and Tool-Use Evaluation in LLM Agent
-
auto-psych: Automating the science of mind using agent-driven theory discovery and experimentation
-
Linguistics and Human Brain: A Perspective of Computational Neuroscience
-
One Voice, Many Tongues: Cross-Lingual Voice Cloning for Scientific Speech
-
Einstein World Models
-
Extracting Neural Materials from Multi-view Images
-
AIGP: An LLM-Based Framework for Long-Term Value Alignment in E-Commerce Pricing
-
Fortress and Gatekeeper: Theorizing Transitive Trust in Third-Party Cybersecurity Risk Governance
-
CORTEX: A Structured Reasoning Benchmark for Trustworthy 3D Chest CT MLLMs
-
COrigami: An AI Pipeline for Co-Designing Flat-Foldable Visually Recognisable Origami
-
OmniRobotHome: A Multi-Camera Home Platform for Real-Time Human-Robot Interaction
-
Sutra: Tensor-Op RNNs as a Compilation Target for Vector Symbolic Architectures
-
Soft Token Alignment for Cross-Lingual Reasoning
-
Jailbreaking for the Average Jane: Choosing Optimal Jailbreaks via Bandit Algorithms for Automatically Enhanced Queries
-
Can Large Language Models Reliably Code Qualitative Humanitarian Data? A Benchmark Study Against Human Expert Adjudication
-
Breaking Data Symmetry is Needed For Generalization in Feature Learning Kernels
-
FUTO Swipe: Layout-Agnostic Neural Swipe Decoding
-
AMVICC: A Novel Benchmark for Cross-Modal Failure Mode Profiling for VLMs and IGMs
-
OracleAnalyser: Analysing Implicit Semantics of Oracle Bone Scripts through MLLMs with Post-training
-
Automatic Generation of Highlights for Academic Paper Via Prompt-based Learning
-
AI translation of literary texts is "fine", but readers still prefer human translations
-
CN-NewsTTS Bench: a target-level automatic benchmark for raw-input Chinese news TTS pronunciation
-
REALM: A Unified Red-Teaming Benchmark for Physical-World VLMs
-
AI Fiction in the Wild
-
Open-source LLMs administer maximum electric shocks in a Milgram-like obedience experiment
-
Self-Recognition Finetuning can Prevent and Reverse Emergent Misalignment
-
A P\={a}ninian Foundation for Indic Language Processing
-
ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs
-
HiPath: Hierarchical Vision-Language Alignment for Structured Pathology Report Prediction
-
NRITYAM: Language Models Meet Art and Heritage of Dance
-
Secure Coding Drift in LLM-Assisted Post-Quantum Cryptography Development: A Gamified Fix
-
HGCN(O): A Self-Tuning GCN HyperModel Toolkit for Outcome Prediction in Event-Sequence Data
-
REDACT: A Systematically Controlled Multilingual Benchmark for Personal Information Detection
-
DeepForestVisionV2: Ecology-Driven Taxonomy Expansion for Camera-Trap Monitoring in African Tropical Forests
-
Cinematic Compositing Using Character-Environment-Harmonized Video Generation Models
-
Thinking in Boxes: 3D Editing in Real Images Made Easy
-
PCFootprint: A Large-Scale Dataset and Benchmark for Vectorized Building Footprint Extraction from Aerial LiDAR Point Clouds
-
CombEval: A Framework for Evaluating Combinatorial Counting in Large Language Models
-
Calibration Without Comprehension: Diagnosing the Limits of Fine-Tuning LLMs for Vulnerability Detection in Systems Software
-
UltraQuant: 4-bit KV Caching for Context-Heavy Agents
-
Benchmarking Agentic Review Systems
-
Where Did the Variability Go? From Vibe Coding to Product Lines by Regeneration
-
Guava: An Effective and Universal Harness for Embodied Manipulation
-
AI-Driven Assessment of Human Tutors: Linking Training Performance to Real-Life Practice
-
TW-LegalBench: Measuring Taiwanese Legal Understanding
-
Dynamic In-Group Persona Generation for Enhancing Human-AI Rapport
-
DeepInflation: an AI agent for research and model discovery of inflation
-
RegMix-D: Dynamic Data Mixing via Proxy Training Trajectories
-
FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs
-
Taming I2V models for Image HOI Editing: A Cognitive Benchmark and Agentic Self-Correcting Framework
-
AMALIA-VL: A Native European Portuguese Open-Source Vision and Language Model
-
Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance
-
Evaluating Prompting-Based Defenses Against Domain-Camouflaged Injection Attacks
-
EgoCS-400K: An Egocentric Gameplay Dataset for World Models
-
Can LLMs Be CEOs? Benchmarking Strategic Resource Reallocation with Multi-Role Agent Simulation
-
Are you speaking my languages? On spoken language adherence in multimodal LLMs
-
R1-SyntheticVL: Is Synthetic Data from Generative Models Ready for Multimodal Large Language Model?
-
BadScientist: Can a Research Agent Write Convincing but Unsound Papers that Fool LLM Reviewers?
-
Quantum Cinema: An Interactive Cinematic Exploration of Quantum Computing Hardware via Generative World Models
-
Reward hacking in physical reinforcement learning revealed by turbulent drag reduction
-
Predictive Analytics in E-Commerce for CustomerBehavior Forecasting using hybrid Ret-DNN withXGBoost Model
-
OmniDrive: An LLM-Choreographed Multi-Agent World Model with Unified Latent Co-Compression for Multi-View Driving Video Generation
-
Flux-Guard: Facial Identity Protection using diffusion models
-
Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks
-
A Benchmark for Omni-Modal Reasoning in Long Videos
-
EComAgentBench: Benchmarking Shopping Agents on Long-Horizon Tasks with Distributed Hidden Intent
-
In-Context Environments Induce Evaluation-Awareness in Language Models
-
PreAct: Computer-Using Agents that Get Faster on Repeated Tasks
-
VinQA: Visual Elements Interleaved Long-form Answer Generation for Real-World Multimodal Document QA
-
PromptShift-CRC: Drift-Aware Conformal Risk Control for Foundation Models Under Prompt and Domain Shift
-
Formalize Once, Edit the Rest: Efficient Lean-Based Answer Selection for Math Reasoning
-
TreeGRNG: Binary Tree Gaussian Random Number Generator for Efficient Probabilistic AI Hardware
-
HanDyVQA: A Video QA Benchmark for Fine-Grained Hand-Object Interaction Dynamics
-
MASCOT-Android: A Curated Dataset and Automated Collection Pipeline for Android Malware Source Code Specimens
-
Towards Pareto-Optimal Tool-Integrated Agents with Pareto Ranking Policy Optimization
-
CPS4: Class Prompt driven Semi-Supervised Spine Segmentation with Class-specific Consistency Constraint
-
SceneCraft: Interactive System for Image Editing via Scene Graph
-
MAWARITH: A Dataset and Benchmark for Legal Inheritance Reasoning with LLMs
-
A Unified Definition of Hallucination: It's The World Model, Stupid!
-
Escaping the Cognitive Well: Efficient Competition Math with Off-the-Shelf Models
-
DifFRACT: Diffusion Feature Reconstruction and Attribution for Circuit Tracing
-
Last But Not Least: Boundary Attention CalibratiON for Multimodal KV Cache Compression
-
Rational Sparse Autoencoder
-
MultiMolecule: a modular ecosystem for biomolecular sequence-model workflows
-
A large-scale pipeline for LLM-assisted corpus annotation: variation and change in the English consider construction
-
LiFT: Local Search via Linear Programming for Overfitting-Controlled Transformers
-
Protein Design with Agent Rosetta: A Case Study for Specialized Scientific Agents
-
AmchiBias: Measuring Stereotypical Bias in Goan Identity Groups with a Minimal Pair Dataset in English and Konkani
-
SciOrch: Learning to Orchestrate Expert LLMs for Solving Frontier Multimodal Scientific Reasoning Tasks
-
Automatic Summarization of Doctor-Patient Encounter Dialogues Using Large Language Model through Prompt Tuning
-
FraudSMSWalker: Benchmarking Agentic Large Language Models for SMS-to-Webpage Fraud Detection
-
Who Drifted: the System or the Judge? Anytime-Valid Attribution in LLM Evaluation Pipelines
-
Automated jailbreak attack targeting multiple defense strategies
-
When Do We Need LLMs? A Diagnostic for Language-Driven Bandits
-
When Errors Become Narratives: A Longitudinal Taxonomy of Silent Failures in a Production LLM Agent Runtime
-
A Virtuous AI is an Existential Risk
-
MASLab: A Unified and Comprehensive Codebase for LLM-based Multi-Agent Systems
-
Same-Origin Policy for Agentic Browsers
-
Refusal Beyond a Single Direction: A Preliminary Comparison of Diff-in-Means and INLP
-
Aligned but Stereotypical? How System Prompts Shape Demographic Bias in LLM-Based Text-to-Image Models
-
FoleyGenEx: Unified Video-to-Audio Generation with Multi-Modal Control, Temporal Alignment, and Semantic Precision
-
Neither Parallel Nor Sequential: How DiffusionGemma Actually Commits Tokens
-
MA-ProofBench: A Two-Tiered Evaluation of LLMs for Theorem Proving in Mathematical Analysis
-
Navigating Gigapixel Pathology Images with Large Multimodal Models
-
RogueAI: A Reverse Turing Test for Detecting Licensed AI Deception in Dialogue
-
SkillChain: Closing the Loop on Skill Evolution for Image-Based E-Commerce AI Assistants
-
TokaMark: A Comprehensive Benchmark for MAST Tokamak Plasma Models
-
The KG-ER Conceptual Schema Language
-
Ex-Omni: Enabling 3D Facial Animation Generation for Omni-modal Large Language Models
-
HarnessBridge: Learnable Bidirectional Controller for LLM Agent Harness
-
Zero-source LLM Hallucination Detection with Human-like Criteria Probing
-
PRISMR: Overcoming Parse Collapse in Multimodal Listwise Ranking via Parameterized Representation Internalization
-
An Explainable AI Assistant for Introductory Programming Education: Improving Feedback Reliability with Instructor-AI Collaboration
-
Brick: Spatial Capability Routing for the Mixture-of-Models (MoM) Paradigm
-
A Quantitative Experimental Repeated Measures Study of Training Dynamics in a Small Llama Style Language Model Under a Compute-Aware Token Budget
-
AI SciBrief as a Gateway to Research: A Framework for Onboarding Students into New Research Areas
-
PI-Hunter: Automated Red-Teaming for Exposing and Localizing Prompt Injections
-
WildIFEval: Instruction Following in the Wild
-
Does Capability Transfer to Subjective Behavior -- and Would Our Instruments Tell Us? A Self-Evolving, Trust-by-Construction Evaluation Paradigm
-
Trust and Reliance on AI in Education: AI Literacy and Need for Cognition as Moderators
-
HarDBench: A Benchmark for Draft-Based Co-Authoring Jailbreak Attacks for Safe Human-LLM Collaborative Writing
-
Scaling Self-Supervised Speech Models Uncovers Deep Linguistic Relationships: Evidence from the Pacific Cluster
-
RAT: Reference-Augmented Training for ASV Anti-Spoofing
-
BadRobot: Jailbreaking Embodied LLM Agents in the Physical World
-
How can we assess human-agent interactions? Case studies in software agent design
-
Failure Modes of Deep Multi-Agent RL in Asynchronous Pricing: Reproducible Triggers, Trace Diagnostics, and a Partial Fix
-
Expert-Level Crisis Detection in Mental Health Conversations
-
NOVA: Symbolic Regression Discovery of Interpretable Car-Following and Lane-Change Models with Driver Heterogeneity
-
CoTAL: Human-in-the-Loop Prompt Engineering for Generalizable Formative Assessment Scoring and Feedback
-
The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent Misalignment
-
Architect-Ant: Editable Automatic Furnishing of Architectural Floor Plans
-
Structure from Reasoning, Numbers from Search: On-Premise Open LLMs as Structural Priors for Coupled MIMO Controller Tuning
-
An LLM-Native Psychometric Instrument Does Not Predict LLM Behavior: Evidence Across 25 Models
-
CleanPatrick: A Benchmark for Image Data Cleaning
-
FOGO: Forgetting-aware Orthogonalization Optimizer
-
Multimodal Large Language Models as Synthetic Participants in Video-Based Studies: An Evaluation
-
Momentum for Reasoning: Dense Intrinsic Signals in Policy Optimization
-
Self-Evolving Scientific Agent Discovers Generalizable Physically-Reasoned Fluid Control
-
Contract2Tool: Learning Preconditions and Effects for Reliable Tool-Augmented LLM Agents
-
The CIFAR Synthetic Evidence Corpus for Detecting AI-Generated Evidence
-
Overcoming the Regulatory Bottleneck via Agent-to-Agent Protocols: A Nuclear Case Study
-
RetroReasoner: A Reasoning LLM for Strategic Retrosynthesis Prediction
-
Sycophancy as a Multilingual Alignment Failure: How Safety Degrades Across Languages, Topics, and Models
-
GIScholarBench: Benchmarking LLM Overconfidence in GIS Research
-
Vision Language Model Helps Private Information De-Identification in Vision Data
-
Data Agents Under Attack: Vulnerabilities in LLM-Driven Analytical Systems
-
EditSR: Enhancing Neural Symbolic Regression via Edit-based Rectification
-
MIRAGE: Metadata-Integrated Repository Analysis and Guided Enhancement for MSR Datasets
-
What neurosurgeons need to see: synthetic intra-operative MRI from ultrasound for brain-shift compensation in brain tumour surgery
-
Transfer learning for causal forest
-
Collaborative Human-Agent Protocol (CHAP)
-
DIYHealth Suite: Dataset, Model, and Benchmark for Health Management at Home
-
Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?
-
BLUE: Toward Better Language Use in Efficient Vision-Language-Action Models for Autonomous Driving
-
GimmBO: Interactive Generative Image Model Merging via Bayesian Optimization
-
Insertion Based Sequence Generation with Learnable Order Dynamics
-
CodeTaste: Can LLMs Generate Human-Level Code Refactorings?
-
A Comparative Study of Student Perspectives on Technical Writing Feedback Quality: Evaluating LLMs, SLMs, and Humans in Computer Science Topics
-
Context Over Compute Human-in-the-Loop Outperforms Iterative Chain-of-Thought Prompting in Interview Answer Quality
-
WhiteTesseract: Reframing the Interpretation of Cultural Heritage through XR and Conversational AI
-
OrderDP: A Theoretically Guaranteed Lossless Dynamic Data Pruning Framework
-
AliyunConsoleAgent: Training Web Agents in Real-World Cloud Environments via Distillation and Reinforcement Learning
-
FieldWorkArena: Agentic AI Benchmark for Real Field Work Tasks
-
Playing Devil's Advocate: Off-the-Shelf Persona Vectors Rival Targeted Steering for Sycophancy
-
ADAGE: Active Defenses Against GNN Extraction
-
Deployed trusted-node quantum key distribution over 300 km with a multi-core fiber access link
-
You Only Landmark Once: Lightweight U-Net Face Super Resolution with YOLO-World Landmark Heatmaps
-
Should You Use Your Large Language Model to Explore or Exploit?
-
Database Normalization via Dual-LLM Self-Refinement
-
Evaluating AI-based Scientific Knowledge Synthesis with Epidemiological Systematic Reviews
-
Training for Technology: Adoption and Productive Use of Generative AI in Legal Analysis
-
OGA-AID: Clinician-in-the-loop AI Report Drafting Assistant for Multimodal Observational Gait Analysis in Post-Stroke Rehabilitation
-
SEEK: Steering LLM Reasoning for RAG via Internal Reasoning Sketches
-
Phun-Bench: Evaluating LLMs on Phonological Understanding in Chinese
-
When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness
-
It's a TRAP! Task-Redirecting Agent Persuasion Benchmark for Web Agents
-
Limitations of Normalization in Attention Mechanism
-
Zero-Shot Embedding Drift Detection: A Lightweight Defense Against Prompt Injections in LLMs
-
EVA: Evolving Semantic Adversaries for Red-Teaming GUI Agents Against Environmental Injection Attacks
-
KIT's Submission to Cross-Lingual Voice Cloning in IWSLT 2026
-
Dash2Sim: Closed-Loop Driving Simulation from in-the-wild Dashcam Videos
-
WorldBench: A Challenging and Visually Diverse Multimodal Reasoning Benchmark
-
Automatic Causal Fairness Analysis with LLM-Generated Reporting
-
MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMs
-
Harnessing AtomisticSkills for Agentic Atomistic Research
-
AnE: Pushing the Reasoning Frontier of Multimodal LLMs via Anchor Evolution
-
Multi-Persona Debate System for Automated Scientific Hypothesis Generation
-
SimuWoB: Simulating Real-World Mobile Apps for Fast and Faithful GUI Agent Benchmarking
-
SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research