Entities · Products
ScienceCast
342 articles tagged with this entity.
-
Towards Understanding Steering Strength
-
DiffCVE: Diffusion-based Compressed Video Enhancement
-
Think Big, Search Small: Where Capacity Matters in Hierarchical Search Agents?
-
Pelican-VLA 0.5: Attending Before Acting Benefits Generalization
-
Infinite Worlds with Versatile Interactions
-
Non-contact, Real-time, Heart-rate Measurement using Image Processing with Commodity Cameras and AI Agents
-
From Noisy Traces to Root Causes: Structural Trajectory Analysis and Causal Extraction for Agent Optimization
-
WildCity: A Real-World City-Scale Testbed for Rendering, Simulation, and Spatial Intelligence
-
Participatory provenance as representational auditing for AI-mediated public consultation
-
VASP Agent: An Agentic Framework for Autonomous First-principles Calculations
-
Faithful or Findable? Evaluating LLM-Generated Metadata for RDF Dataset Search
-
Evaluating calibrated refusal and safe usefulness in dual-use biology settings
-
A Guiding Framework for K-12 Teachers in Creating AI-powered Learning Technologies through Vibe Coding
-
Position: Preventing AI-Generated CSAM Necessitates New Approaches to AI Safety
-
Reliable Mislabel Detection for Video Capsule Endoscopy Data
-
i-EXAM: Instructable and Explainable Attack Connectivity Graph Modeler
-
An Experimental Design Approach to Evaluating Agentic AI's Autonomous Model Discovery
-
Automated Compliance Mapping in Cloud Security with Domain-Adapted Sentence Transformers
-
Multi-Task Instruction Tuning via Data Scheduling for Low-Resource Arabic SpeechLLMs
-
Channel-wise Retrieval for Multivariate Time Series Forecasting
-
The relationship between reasoning and performance in large language models--o3 (mini) thinks harder, not longer
-
ROK-FORTRESS: Measuring the Effect of Geopolitical Transcreation for National Security and Public Safety
-
Moonstone: A Multimodal Foundation Model and Benchmark for Lunar Remote Sensing
-
PromptPET: Privacy-Utility Optimized Prompt Obfuscation
-
Don't Wait to Reply: Towards Responsive yet Thoughtful Dialogue through Proactive Thinking
-
Revealing Hidden Model Behaviors with Task-Specific Self-Reports
-
Predicting the Emergence of Induction Heads in Language Model Pretraining
-
Geometry of Ordinal Representations in Language Models
-
Knowledge-Centric Information Systems
-
VKnowU: Evaluating Visual Knowledge Understanding in Multimodal LLMs
-
Phi-SegNet: Phase-Integrated Supervision for Medical Image Segmentation
-
Piercing Gilbreath's Conjecture: From Deep Number Theory Insights to Fintech and Cybersecurity
-
IRIS: An Intelligent Vision-Language System for Ocular Surface Diseases via Topic Tree and Scene-Driven VQA Generation
-
Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation
-
A Precedent-Guided Co-Scientist for Side-Effect-Aware Drug Redesign
-
SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses
-
MAGE: View-guided Point Cloud Completion with Efficient Modality Alignment and Adaptive Geometry Enhancement
-
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
-
Determinants and Limits of LLM Security-Tool Orchestration: A Study with HexStrike-AI
-
Builder, Defender, Breaker: The Case Against Removing the Human from the AI-Driven Security Lifecycle
-
EM3M: An Electron Micrograph Dataset for Microstructural Segmentation and Generation
-
Anchored Self-Play for Code Repair
-
A Fair Benchmarking of Deep Relational Database Learning Models
-
Agent Step Value: State-Transition Measurement with State-Grounded LLM Evaluators
-
Toward Trustworthy Large Language Model Agents in Healthcare
-
Attention Limited Reward Learning
-
PraMem: Practice-derived Experiential Memory for Long-horizon Behavior Prediction
-
When Do Foundation Models Pay Off? A Break-Even Analysis of Pretrained Time Series Forecasters
-
Human-Centric Reflective Architecture for Human-AI Collaborative Decision-Making
-
SPORK: Self-Speculative Forking to Accelerate Agentic LLM Inference
-
What is Left for Us? Second Scholarship Against the Degradation of Research by AI
-
DistillH-Mamba: A Hypergraph-Mamba-Based Knowledge Distillation Model for Efficient Impact Fall Detection
-
Trust-Region Noise Search for Black-Box Alignment of Diffusion and Flow Models
-
PLACEMEM: Toward a Compute-Aware Memory Plane for Lifelong Agents
-
MechMath Agent Team: LLM Driven Agents for Mathematical Research
-
Weighted Conformal Prediction for Lab-to-Track Thermal Transfer in EV Motorsport Powertrains
-
Transformer Geometry Observatory TGO-II: Representational Similarity Observatory
-
A Storm-Centric 250 m NEXRAD Level-II Dataset for High-Resolution ML Nowcasting
-
PPTArena: A Benchmark for PowerPoint Editing
-
SpaceEra++: A Unified Framework Towards 3D Spatial Reasoning in Video
-
Computer Vision for Wildlife Monitoring: Detecting Brown Howler Monkeys using YOLO
-
TCG-AR: Real-Time Multi-View Augmented Reality for Trading Card Game Streaming
-
Beyond Skepticism: Evaluating LLMs Pedagogical Intent Reasoning with the Adaptive Pedagogical Vigilance Framework
-
SINA: A Fully Automated Circuit Schematic Image to Netlist Generator Using Artificial Intelligence
-
Multi-THuMBS: Multi-person Tracking of 3D Human Meshes Beyond Video Shots
-
PreScience: A Dataset and Benchmark for Scientific Forecasting
-
AEGIS: A Multi-Task Joint-Embedding Predictive Architecture for Mammography
-
Understanding Why Language Models Hallucinate: Testing Reasoning Against Priors
-
LV-ROVER: Multi-Stream Tesseract Voting for Maltese Paragraph OCR
-
When Context Compensates for Sparse Event History: AlphaEarth for Spatio-Temporal Point-Process Forecasting
-
Utilizing Earth Foundation Models to Enhance the Simulation Performance of Hydrological Models with AlphaEarth Embeddings
-
Planning over MAPF Agent Dependencies via Multi-Dependency PIBT
-
MolSafeEval: A Benchmark for Uncovering Safety Risks in AI-Generated Molecules
-
Quantifying the Affective Gap: A Zero-Shot Evaluation of LLMs on Fine-Grained Emotion Taxonomies
-
AGI Maze as a Benchmark Framework for World-Modeling Agents
-
ATM: CID-Brokered Pre-Write Admission for Multi-Agent Code Co-Synthesis
-
Multi-Turn Agentic Scientific Literature Search via Workflow Induction
-
Play Like Champions: Counterfactual Feedback Generation in Latent Space
-
Two AI Metrics Diverged: Will it Make All the Difference?
-
ZEBRA: Zero-Shot Entropy-Regularized Prompt Learning for Base-to-Novel Generalization in Audio-Language Models
-
The Consistency Dilemma in LLMs: Generator-Evaluator Agreement and Vulnerability to Mistakes
-
Large Databases Need Small, Open-Weight Language Models
-
BayesBench: Evaluating LLM Belief Trajectories Under Multi-Turn Evidence Accumulation
-
Measuring Judgment Quality in Natural-Language Explanations: Evidence from Forecasting Tournaments
-
Efficient Public Verification of Private ML via Regularization
-
DSIP: A Dynamic Coordination Planner for Signal-Free Intersections using Diffusion-Model-Based Multi-Agent Motion Planning
-
Triospect: A Three-Dimensional Framework for Robust Statistical AI-Generated Text Detection Against Diverse Attacks
-
ReplicatorBench: Benchmarking LLM Agents for Replicability in Social and Behavioral Sciences
-
An Agentic AI Pipeline for Appliance-Level Energy Anomaly Detection and LLM-Driven Recommendations
-
MixSarc: A Bangla-English Code-Mixed Corpus for Implicit Meaning Identification
-
Unveiling Novelty Evolution in the field of Library and Information Science in China
-
Animation2Code: Evaluating Temporal Visual Reasoning in Video-to-Code Generation
-
PIXELRAG: Web Screenshots Beat Text for Retrieval-Augmented Generation
-
Neuromorphic Energy-Aware Learning for Adaptive Deep Brain Stimulation
-
Complete virtual unwrapping and reading of a rolled Herculaneum papyrus
-
Your Data Manifold is Secretly a Reward Model: Shell-LCC for Text-to-Video Generation
-
Transolver-3: Scaling Up Transformer Solvers to Industrial-Scale Geometries
-
HomeDiffusion: Zero-Shot Object Customization with Multi-View Representation Learning for Indoor Scenes
-
Is Lying an Emergent Behaviour in LLMs? Evidence from Gaslighting AI agents in a Sustainability Game
-
TrafficAlign: Aligning Large Language Models for Traffic Scenario Generation
-
SrDetection: A Self-Referential Framework for Data Leakage Detection in Code Large Language Models
-
Grounding LLM Reasoning under Incomplete Graph Evidence
-
Neural Procedural Memory: Empowering LLM Agents with Implicit Activation Steering
-
Friend or Foe
-
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
-
Depth Exploration for LLM Decoding
-
ASTAD: Asymmetric Style Transfer for Synthetic-to-Real Adaptation in Autonomous Driving
-
From Local Windows to Adaptive Candidates via Individualized Exploratory: Rethinking Attention for Image Super-Resolution
-
To Tab or Not to Tab: Measuring Critical Engagement in AI Code Completion Tools Using Behavioral Signals and Attention Checks
-
GLIP: Graph and LLM Joint Pretraining for Graph-Level Tasks
-
SpreadsheetBench 2: Evaluating Agents on End-to-End Business Spreadsheet Workflows
-
A Hybrid Framework For Crypto-Ransomware Detection In Enterprise Shared Storage
-
HiComm: Hierarchical Communication for Multi-agent Reinforcement Learning
-
AI Trading's Alpha Singularity: Emergent Market Reasoning through Agent-to-Agent Self-Evolution
-
Faults in Our Formal Benchmarking: Dataset Defects and Evaluation Failures in Lean Theorem Proving
-
Argus: Metric Panoramic 3D Reconstruction for Indoor Scenes
-
Proof-of-Guardrail in AI Agents and What (Not) to Trust from It
-
ML-Powered LDAP Reconnaissance Detection using Weak Supervision
-
Enhanced Diffusion Sampling: Efficient Rare Event Sampling and Free Energy Calculation with Diffusion Models
-
HunyuanImage 3.0 Technical Report
-
MindFlow: Harmonizing Cognitive Semantics and Acoustic Dynamics for Facial Animation Generation in Dyadic Conversations
-
"Generate" the Future of Work through AI: Empirical Evidence from Online Labor Markets
-
SpaceDG: Benchmarking Spatial Intelligence under Visual Degradation
-
Fine-tuning a multimodal large language model for clinician-grade autism behavioral scoring from short home videos
-
HumanMoveVQA: Can Video MLLMs reason about human movement in videos?
-
LieSolver: PDE-Constrained Learning for IBVPs via Lie Symmetries
-
When Does Personality Composition Matter for Multi-Agent LLM Teams?
-
Agentic Publication Protocol: An Attempt to Modernize Scientific Publication
-
Does Aurora Encode Atmospheric Structure? Latent Regime Analysis and Attribution
-
A Pipeline for Generating Longitudinal Synthetic Clinical Notes Using Large Language Models
-
AgentX: Towards Agent-Driven Self-Iteration of Industrial Recommender Systems
-
RoPEMover: Depth-Aware Object Relocation via Positional Embeddings
-
ConflictScore: Identifying and Measuring How Language Models Handle Conflicting Evidence
-
Narration-of-Thought: Inference-Time Scaffolding for Defeasible Ethical Reasoning in Large Language Models
-
ProfileFoundry: A Synthetic Person-Object Substrate for Privacy, Memory, and Tool-Use Evaluation in LLM Agent
-
Staying VIGILant: Mitigating Visual Laziness via Counterfactual Visual Alignment in MLLMs
-
auto-psych: Automating the science of mind using agent-driven theory discovery and experimentation
-
Detecting and Controlling Sycophancy with Cascading Linear Features
-
Linguistics and Human Brain: A Perspective of Computational Neuroscience
-
Context Recycling for Long-Horizon LLM Inference
-
COrigami: An AI Pipeline for Co-Designing Flat-Foldable Visually Recognisable Origami
-
OmniRobotHome: A Multi-Camera Home Platform for Real-Time Human-Robot Interaction
-
Soft Token Alignment for Cross-Lingual Reasoning
-
Can Large Language Models Reliably Code Qualitative Humanitarian Data? A Benchmark Study Against Human Expert Adjudication
-
MacroLens: A Multi-Task Benchmark for Contextual Financial Reasoning under Macroeconomic Scenarios
-
Scalable Peptide Design via Memory-Efficient Equivariant Transformer
-
A Probabilistic Framework for LLM-Based Model Discovery
-
Kuramoto Oscillatory Phase Encoding: Neuro-inspired Synchronization for Improved Learning Efficiency
-
AMVICC: A Novel Benchmark for Cross-Modal Failure Mode Profiling for VLMs and IGMs
-
Beyond Visual Forensics: Auditing Multimodal Robustness for Synthetic Medical Image Detection
-
HG-Bench: A Benchmark for Multi-Page Handwritten Answer-Region Grounding in Automated Homework Assessment
-
ShutterMuse: Capture-Time Photography Guidance with MLLMs
-
A Survey of Toxicity Detection and Mitigation Strategies for Multilingual Language Models
-
Measuring Research Difficulty of Academic Papers: A Case Study in Natural Language Processing
-
Neural operator-based digital twins for modeling amyloid-$\beta$ and tau propagation and treatment optimization in Alzheimer's disease
-
Preferences of a Voice-First Nation: Large-Scale Pairwise Evaluation and Preference Analysis for TTS in Indian Languages
-
VieSpeaker: A Large-Scale Vietnamese Speaker Recognition Dataset Beyond Visual Dependency
-
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
-
A P\={a}ninian Foundation for Indic Language Processing
-
Grading the Grader: Lessons from Evaluating an Agentic Data Analysis System
-
Predicting Poets' Origins from Verse: A Computational Analysis of Regional Linguistic Fingerprints in the Complete Tang Poems
-
MedBench v5: A Dynamic, Process-Oriented, and Hallucination-Aware Benchmark for Clinical Multimodal Models
-
Exploring Academic Influence of Algorithms by Co-occurrence Network Based on Full-text of Academic Papers
-
Can Language Model Agents be Helpful Circuit Explainers in Mechanistic Interpretability?
-
Data Scale, Not Latency, Shapes Cross-Lingual Encoder Transfer in Streaming ASR
-
NRITYAM: Language Models Meet Art and Heritage of Dance
-
The Hidden Environmental Cost of Poor Coding Practices in TensorFlow and Keras Applications: A Study on Resource Leaks and Carbon Emissions
-
HGCN(O): A Self-Tuning GCN HyperModel Toolkit for Outcome Prediction in Event-Sequence Data
-
StylisticBias: A Few Human Visual Cues Drive Most Social Biases in MLLMs
-
Cinematic Compositing Using Character-Environment-Harmonized Video Generation Models
-
HEad and neCK TumOR (HECKTOR) 2025: Benchmark of Segmentation, Diagnosis, and Prognosis in Multimodal PET/CT
-
Thinking in Boxes: 3D Editing in Real Images Made Easy
-
SAFE-Cascade: Cost-Adaptive Vision-Language Routing for Chart Question Answering
-
Emergent Alignment
-
Data Standards for Humanoid Robotics: The Missing Infrastructure for Physical AI
-
Bidirectional Tutoring for Developmental Motor Learning in Robots: Co-Developed Interaction Dynamics Support Stable Learning
-
Calibration Without Comprehension: Diagnosing the Limits of Fine-Tuning LLMs for Vulnerability Detection in Systems Software
-
Simulation of Language Evolution under Regulated Social Media Platforms: A Synergistic Approach of Large Language Models and Genetic Algorithms
-
Self-Adaptive Scale Handling for Forecasting Time Series with Scale Heterogeneity
-
Multi-LCB: Extending LiveCodeBench to Multiple Programming Languages
-
PASQA: Pitch-Accent-Focused Speech Quality Assessment Model Trained on Synthetic Speech with Accent Errors
-
Multi-Head Attention-Based Feature Extractor Integration with Soft Actor-Critic for Porosity Prediction and Process Parameter Optimization in Additive Manufacturing
-
Where Did the Variability Go? From Vibe Coding to Product Lines by Regeneration
-
As Easy as Rocket Science: Assessing the Ability of Large Language Models to Interpret Negation in Figurative Language
-
GrowthHacker: Automated Off-Policy Evaluation Optimization Using Code-Modifying LLM Agents
-
PosterForest: Hierarchical Multi-Agent Collaboration for Scientific Poster Generation
-
G-IdiomAlign: A Gloss-Pivoted Benchmark for Cross-Lingual Idiom Alignment
-
LegalWorld: A Life-Cycle Interactive Environment for Legal Agents
-
PreUnlearn: Auditing Collateral Knowledge Damage Before Large Language Model Unlearning
-
IndicContextEval: A Benchmark for Evaluating Context Utilisation in Audio Large Language Models Across 8 Indic Languages
-
Taming I2V models for Image HOI Editing: A Cognitive Benchmark and Agentic Self-Correcting Framework
-
Optimal scenario design for climate emulation
-
Riemannian MeanFlow for One-Step Generation on Manifolds
-
Using Cognitive Models to Improve Language Model Simulation of Human Persuasion Games
-
Speaking in Self-Assessing Tongues: On the Verbalized Confidence of LLMs in Machine Translation
-
Perceptual compensation for tonal context in self-supervised speech models
-
AI Adoption Across a Multinational Workforce: Sociotechnical Conditions for GenAI Acceptance in Human Resources
-
Seeing Is Not Screening: Multimodal Hidden Instruction Attacks on Agent Skill Scanners
-
A Benchmark for Omni-Modal Reasoning in Long Videos
-
Toward Accessible Psychotherapy Training Using AI-Driven Interactive Patient Avatars
-
EComAgentBench: Benchmarking Shopping Agents on Long-Horizon Tasks with Distributed Hidden Intent
-
ProvenanceGuard: Source-Aware Factuality Verification for MCP-Based LLM Agents
-
When Tables Go Crazy: Evaluating Multimodal Models on French Financial Documents
-
Conditional Local Importance by Quantile Expectations
-
PreAct: Computer-Using Agents that Get Faster on Repeated Tasks
-
Agentic AI-based Framework for Mitigating Premature Diagnostic Handoff and Silent Hallucination in Healthcare Applications
-
Unifying Post-hoc Explanations of Knowledge Graph Completions
-
NeRD: Neuro-Symbolic Rule Distillation for Efficient Ontology-Grounded Chain-of-Thought in Medical Image Diagnosis
-
Structure-aware Knowledge-guided Heterogeneous Mamba for Zygomaticomaxillary Suture Assessment
-
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
-
MIRAGE: Runtime Scheduling for Multi-Vector Image Retrieval with Hierarchical Decomposition
-
How Post-Training Shapes Biological Reasoning Models
-
Oops, Wait: Discourse Tokens Matter in Reasoning Model
-
MAWARITH: A Dataset and Benchmark for Legal Inheritance Reasoning with LLMs
-
Computational Safety for Generative AI: A Hypothesis Testing Perspective
-
DifFRACT: Diffusion Feature Reconstruction and Attribution for Circuit Tracing
-
Last But Not Least: Boundary Attention CalibratiON for Multimodal KV Cache Compression
-
AI Supply Chain Galaxy: 3D Visual Analytics for License Compliance
-
Rational Sparse Autoencoder
-
MultiMolecule: a modular ecosystem for biomolecular sequence-model workflows
-
Tight Bounds for Logistic Regression with Large Stepsize Gradient Descent in Low Dimension
-
TERMS-Bench: Diagnosing LLM Negotiation Agents Beyond Deal Rate
-
Discrimination-free Insurance Pricing with Privatized Sensitive Attributes
-
FlowState: Sampling-Rate-Equivariant Time-Series Forecasting
-
Beyond Text-to-SQL: An Agentic LLM System for Governed Enterprise Analytics APIs
-
SciOrch: Learning to Orchestrate Expert LLMs for Solving Frontier Multimodal Scientific Reasoning Tasks
-
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
-
AIChilles: Automatically Uncovering Hidden Weaknesses in AI-Evolved Systems
-
PAL-Bench: Evidence-Grounded Profile Reconstruction from Longitudinal Personal Albums
-
AgentFairBench: Do LLM Agents Discriminate When They Act?
-
Beyond Correctness: Enhancing Architectural Reasoning in Code LLMs via Scalable Labeling with Agentic Judgment
-
Limited Marginal Benefit of Reasoning-Heavy LLM Deployment in ESG Narrative Scoring: A 4-Model Consensus Study on Japanese Listed Firms
-
Control-Plane Placement Shapes Forgetting: An Architectural Study of Agent Memory Across Thirteen System Configurations
-
DYNA : Dynamic Episodic Memory Networks for Augmenting Large Language Models with Temporal Knowledge Graphs in Continuous Learning
-
Label Shift Aware Adaptation for Online Zero-shot Learning with Contrastive Language-Image Pre-Training (CLIP)
-
Gaming-Resistant Insurance Contracts for Autonomous AI Agents: Strategy-Proof Toll Mechanism Design
-
A Pragmatic VLA Foundation Model
-
When Errors Become Narratives: A Longitudinal Taxonomy of Silent Failures in a Production LLM Agent Runtime
-
Where Black-box Drug-Target Interaction Prediction Models Look: Cross-Method Explainability
-
MET-Bench: Multimodal Entity Tracking for Evaluating the Limitations of Vision-Language and Reasoning Models
-
A Multi-Agent AI System for Automated High School Transcript Processing: Collaborative Document Analysis at Scale
-
Improving Lunar Topography with Deep Learning Schr\"odinger Bridges
-
FoleyGenEx: Unified Video-to-Audio Generation with Multi-Modal Control, Temporal Alignment, and Semantic Precision
-
Can LLMs Accurately Score Medical Diagnoses and Clinical Reasoning?
-
VietFashion: Benchmarking Sketch-Text Composed Image Retrieval for Cultural Outfits
-
Detecting Functional Memorization in Code Language Models
-
M\"OVE: A Holistic LLM Benchmark for the German Public Sector
-
RogueAI: A Reverse Turing Test for Detecting Licensed AI Deception in Dialogue
-
From Passive Generation to Investigation: A Proactive Scientific Peer Review Agent
-
CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges
-
Reconstructing Template-Memorized Images from Natural Prompts
-
Structured Testbench Generation for LLM-Driven HDL Design and Verification-Oriented Data Curation
-
WISE: A Long-Horizon Agent in Minecraft with Why-Which Reasoning
-
Zero-source LLM Hallucination Detection with Human-like Criteria Probing
-
Brick: Spatial Capability Routing for the Mixture-of-Models (MoM) Paradigm
-
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
-
Localizing Anchoring Pathways in Language Models
-
WildIFEval: Instruction Following in the Wild
-
Data Fusion for High-Resolution Estimation
-
It Takes One to Bias Them All: Breaking Bad with One-Shot GRPO
-
UniPET: a universal network for high-quality PET image denoising across varied dose reduction factors
-
Swivuriso: The South African Next Voices Multilingual Speech Dataset
-
Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation
-
HarDBench: A Benchmark for Draft-Based Co-Authoring Jailbreak Attacks for Safe Human-LLM Collaborative Writing
-
MemVenom: Triggered Poisoning of Multimodal Memories in Web Agents
-
BadRobot: Jailbreaking Embodied LLM Agents in the Physical World
-
Interpreting and Steering a Text-to-Speech Language Model with Sparse Autoencoders
-
Catching One in Five: LLM-as-Judge Blind Spots in Production Multi-Turn Transaction Agents
-
Expert-Level Crisis Detection in Mental Health Conversations
-
Using the YOLOv12 Model for Verifying the Correct Color Sequence of Wires in Network Cables (Patch Cords) on the Production Line
-
Who Wrote the Book? Detecting and Attributing LLM Ghostwriters
-
Regimes: An Auditable, Held-Out-Gated Improvement Loop Demonstrated on LongMemEval with ActiveGraph
-
The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent Misalignment
-
Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution
-
Deployment-Time Memorization in Foundation-Model Agents
-
Evaluating Research-Level Math Proofs via Strict Step-Level Verification
-
Do VLMs Reason Like Engineers? A Benchmark and a Stage-wise Evaluation
-
CleanPatrick: A Benchmark for Image Data Cleaning
-
++nnU-Net: Scaling nnU-Net with Prefix-Based Data Augmentation
-
FOGO: Forgetting-aware Orthogonalization Optimizer
-
SAW: Stage-Aware Dynamic Weighting for Multi-Objective Reinforcement Learning in Large Language Models
-
MemoVAD: Resource-Efficient Video Anomaly Detection via Dynamic Semantic Memory in Edge Computing Scenarios
-
MatMind: A Structure-Activity Knowledge-Driven Generative Foundation Model for Materials Science
-
GraphLoRA: Structure-Aware Low-Rank Adaptation for Large Language Model Recommendation
-
SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks
-
Momentum for Reasoning: Dense Intrinsic Signals in Policy Optimization
-
Contract2Tool: Learning Preconditions and Effects for Reliable Tool-Augmented LLM Agents
-
Beyond Goodhart's Law: A Dynamic Benchmark for Evaluating Compliance in Multi-Agent Systems
-
ArtiFact: A Large-Scale Multi-Modal Cultural Heritage Dataset
-
Kunlun: Establishing Scaling Laws for Massive-Scale Recommendation Systems through Unified Architecture Design
-
Distilling Safe LLM Systems via Soft Prompts for On Device Settings
-
Sycophancy as a Multilingual Alignment Failure: How Safety Degrades Across Languages, Topics, and Models
-
EditSR: Enhancing Neural Symbolic Regression via Edit-based Rectification
-
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?
-
ChinaHeritaQA: A Culturally-Grounded Visual Question Answering Dataset for World Heritage Sites in China
-
C$^3$ache: Accelerating World Action Models with Cross Inference Chunk Cache
-
AI-Native Closed-Loop Security for 6G-Enabled Cyber-Physical Systems: From Edge Detection to Network-Wide Mitigation
-
IR-SIM: A Lightweight Skill-Native Simulator for Navigation, Learning, and Benchmarking
-
Do Larger Models Really Win in Drug Discovery? A Benchmark Assessment of Model Scaling in AI-Driven Molecular Property and Activity Prediction
-
CodeTaste: Can LLMs Generate Human-Level Code Refactorings?
-
Automated Framework to Evaluate and Harden LLM System Instructions against Encoding Attacks
-
Decoding Naturalistic Emotion Dynamics from the Brain: An LLM-Enhanced Regression Framework
-
Order Matters: Unveiling the Hidden Impact of Macro Placement Sequences via Proxy-Guided LLM Evolution
-
Sample-Efficient LLM-Based Detection of Malicious Web Server Logs with Forensically Explainable Reasoning
-
SafeRun: Enabling Determinism in LLM Planning for Running
-
Safe-RULE: Safe Reinforcement UnLEarning
-
TQA-Bench: Evaluating LLMs for Multi-Table Question Answering
-
Playing Devil's Advocate: Off-the-Shelf Persona Vectors Rival Targeted Steering for Sycophancy
-
Chunking the Critic: A Transformer-based Soft Actor-Critic with N-Step Returns
-
Learning Explicit Behavioral Models with Adaptive Questions and World-Model Probes
-
OpenSkill: Open-World Self-Evolution for LLM Agents
-
DyCon: Dynamic Reasoning Control via Evolving Difficulty Modeling
-
Training for Technology: Adoption and Productive Use of Generative AI in Legal Analysis
-
Korean Culture into LLM Alignment: Toward Cultural Coherence
-
Quantifying Media Representation Dynamics Across 25 Years of News Reporting on Policing-related Deaths
-
Explicit Evidence Grounding via Structured Inline Citation Generation
-
Meaning in Order, Order in Meaning: Semantic R-precision for Keyphrase Evaluation
-
Hearing the Unspoken: Language Model Priors for Acoustic Adversarial Attacks
-
Depth over Fidelity in Fixed-Budget Noisy Evolution Strategies
-
Trio: Learning Time-Series Forecasting with Temporal-Spatial-Sample Attention and Structural Causal Priors
-
Re-Centering Humans in LLM Personalization
-
WorldBench: A Challenging and Visually Diverse Multimodal Reasoning Benchmark
-
Real-Time AttentionBender: Granular Interactive Network Bending of Video Diffusion Transformers
-
Harnessing AtomisticSkills for Agentic Atomistic Research
-
Why We Need World Models for AGI: Where LLMs Fail and How World Models May Outperform
-
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