Entities · Models
GPT-4o
124 articles tagged with this entity.
-
Introducing GPT‑Live
-
BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech
-
Detoxify: A framework for abusive text transformation using LLMs
-
Native-speed vLLM transformers modeling backend
-
Decomposed Prompting Does Not Fix Knowledge Gaps, But Helps Models Say "I Don't Know"
-
Programming over Thinking: Efficient and Robust Multi-Constraint Planning
-
SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards
-
EmoteGPT: 3D Human Facial Expressions from Natural Language Descriptions
-
How Utilitarian Are OpenAI's Models Really? Replicating and Reinterpreting Pfeffer, Kr\"ugel, and Uhl (2025)
-
Coverage-Controlled Preference Mining from Noisy Claim Verification for Evidence-Grounded Generation
-
AI Wizards at EXIST 2026: Hierarchical Soft-Label Learning for Multimodal Sexism Identification in Memes
-
Reward Granularity in RLVR: Comparing Process and Outcome Reward Structures for Mathematical Reasoning in Small Language Models
-
Retroactive Chain-of-Thought (RetroCoT): Forensic Reconstruction Prompts as a Safety Diagnostic Across Model Generations
-
MT-EditFlow: Reinforcement Learning for Multi-Turn Image Editing with Flow Matching
-
The only AI glossary you’ll need this year
-
Evaluating Vision-Language Models as a Zero-Shot Learning Alternative to You Only Look Once and Optical Character Recognition for Nigerian License Plate Recognition
-
Multilingual Prompt Localization for Agent-as-a-Judge: Language and Backbone Sensitivity in Requirement-Level Evaluation
-
Distributed Attacks in Persistent-State AI Control
-
The Dual Nature of LLM Persona: Aggregated Tendencies and Frame-Dependent Geometry
-
Beyond Skepticism: Evaluating LLMs Pedagogical Intent Reasoning with the Adaptive Pedagogical Vigilance Framework
-
MMIR-TCM: Memory-Integrated Multimodal Inference and Retrieval for TCM Clinical Decision Support
-
EPC: A Standardized Protocol for Measuring Evaluator Preference Dynamics in LLM Agent Systems
-
Toward Cybersecurity-Expert Small Language Models
-
AutoTrainess: Teaching Language Models to Improve Language Models Autonomously
-
Disentangling Reasoning Logic to Resolve Explicit Knowledge Conflicts
-
Certified Speculative Execution for Untrusted AI Agents
-
HERO: Improving the Reliability and Sensitivity of Generative Model Evaluation Using Historical Data
-
Research Entity Extraction and Topic Detection from UKRI Grant Proposals
-
Seed-to-Seed: Unpaired Image Translation in Diffusion Seed Space
-
Search for Truth from Reasoning: A Dynamic Representation Editing Framework for Steering LLM Trajectories
-
The Digital Afterlife of Empires: Four Language Models Converge on the Same Imperial Cartography of Writing
-
Deterministic Decisions for High-Stakes AI. A Zero-Egress Pipeline with the Deployability of RAG and the Accuracy of Machine Learning
-
SEVA: Self-Evolving Verification Agent with Process Reward for Fact Attribution
-
Multimodal Evaluator Preference Collapse: Cross-Modal Coupling in Self-Evolving Agents
-
CalBrief: A Pilot Diagnostic Benchmark for Evidence-Calibrated Scientific Briefing with Large Language Models
-
Which tokens does a hybrid model predict better?
-
Cliff Tokens: Identifying Single-Token Failure Triggers in LLM Mathematical Reasoning
-
Membox: Weaving Topic Continuity into Long-Range Memory for LLM Agents
-
RoboAtlas: Contextual Active SLAM
-
Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning
-
CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmark
-
VeriPilot: An LLM-Powered Verilog Debugging Framework
-
T2D-Bench: Evidence-Gated Evaluation of LLM Outputs for Type 2 Diabetes Using a Multi-Layer Clinical-Lifestyle Knowledge Graph
-
Poster: Exploring the Limits of Audio-Based Detection of Turkish Phone Call Scams
-
Import AI 462: Superpersuasion; self-sustaining AI; paths to ASI
-
Over-reliance on chatbots can diminish critical-thinking skills, study finds
-
A Layered Security Framework Against Prompt Injection in RAG-Based Chatbots
-
3D-PLOT-LLM: Part-Level Object Tokens for 3D Large Language Models
-
Gender Bias in LLM Hiring Decisions: Evidence from a Japanese Context and Evaluation of Mitigation Strategies
-
S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence
-
Beyond Entropy: Learning from Token-Level Distributional Deviations for LLM Reasoning
-
FAPO: Fully Autonomous Prompt Optimization of Multi-Step LLM Pipelines
-
Examining Human-Like Behaviors in LLMs: A Multi-Dimensional Analysis of Model Behaviors, User Factors, and System Prompts
-
PEC-Home: Interpretation of Progressively Elliptical Commands in Smart Homes
-
CAPRA: Scaling Feedback on Software Architecture Deliverables with a Multi-Agent LLM System
-
LLM-Powered Multi-Agent System for Automated Crypto Portfolio Management
-
Atlas: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning
-
Comparing Human Gaze and Vision-Language Model Attention in Safety-Relevant Environments
-
Multimodal Evaluator Preference Collapse: Cross-Modal Contagion in Self-Evolving Agents
-
The BD-LSC Dataset: Facilitating the Benchmarking of Models for Lexical Semantic Change Detection in Slang and Standard Usage
-
Beyond Accuracy: Measuring Bias Acknowledgment in Chain-of-Thought Reasoning for Responsible AI Evaluation
-
The Quality-Utility Paradox: Why High-Reward Data Impairs Small Model Mathematical Reasoning
-
Is Your Agent Playing Dead? Deployed LLM Agents Exhibit Constraint-Evasive Fabrication and Thanatosis
-
Phishing Email Detection Using Large Language Models
-
LLM4RTL: Tool-Assisted LLM for RTL Generation
-
Compositional Reasoning Depth Predicts Clinical AI Failure: Empirical Evidence Consistent with Transformer Compositionality Limits in Electronic Health Record Question Answering
-
Binary Tracking for Spatial QA and Navigation with Open Vision-Language Models
-
When to Write and When to Suppress: Route-Specialized Dual Adapters for Memory-Assisted Knowledge Editing
-
MARD: Mirror-Augmented Reasoning Distillation for Mechanism-Level Drug-Drug Interaction Prediction
-
DiffusionGemma
-
The Shibboleth Effect: Auditing the Cross-Lingual Distributional Skew of Large Language Models
-
Beyond Model Size: Probing the Gaps in Visual in-Context Learning by Training a Tiny Model
-
What it feels like to work with Mythos
-
An Effective Router for Vision-Language Model Selection
-
FieldWorkArena: Agentic AI Benchmark for Real Field Work Tasks
-
Bridging intent and execution in agentic systems
-
The crash that vanished: control and emergence in a five-model economy
-
ChemQuests: A Curated Chemistry Question-Answer Database Extracted from ChemRxiv papers
-
Will the Agent Recuse Itself? Measuring LLM-Agent Compliance with In-Band Access-Deny Signals
-
Synapse: Federated Tool Routing via Typed Compendium Artifacts
-
DisasterBench: A Multimodal Benchmark for UAV-Based Disaster Response in Complex Environments
-
Ten Headache Specialists versus Artificial Intelligence for Clinical Literature Summarization: A Critical Evaluation and Comparison
-
Using Large Language Models to Support High Volume Application Review for an Undergraduate Research Program
-
PlanBench-V: A Spatial Planning Map Benchmark for Vision-Language Models
-
Med-V1: Small Language Models for Zero-shot and Scalable Biomedical Evidence Attribution
-
Before and After Temperature: A Distributional View of Creative LLM Generation
-
When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning
-
Empathy Applicability Modeling for General Health Queries
-
AnomSeer: Reinforcing Multimodal LLMs to Reason for Time-Series Anomaly Detection
-
ToMAP: Training Opponent-Aware LLM Persuaders with Theory of Mind
-
Truthful AI Advisors: A Pre-Specified Benchmark for Large Language Model Honesty Under Preference Misalignment
-
Med-HEAL: Analyzing and Mitigating Hallucinations in Medical LLMs with Hallucination-Aware In-Context Learning
-
How Generation Architecture Shapes Code Complexity in Multi-Agent LLM Systems: A Paired Study on HumanEval
-
Don't Ask the LLM to Track Freshness: A Deterministic Recipe for Memory Conflict Resolution
-
Send a SCOUT First: Pre-hoc Reasoning for Adaptive Detector Allocation in Prompt-Injection Defense
-
TokTalk: Expressive Real-time Facial Animation from Audio-LLM Tokens
-
FormInv: A Measurement Protocol for Semantic Invariance in Mathematical Reasoning Benchmarks
-
unix-ctf: Procedural Environments for Unix-Competence Reinforcement Learning
-
The Chain Holds, the Answer Folds: Trace-Answer Dissociation in Reasoning Models Under Adversarial Pressure
-
Do Models Know Why They Changed Their Mind? Interpretability and Faithfulness of Chain-of-Thought Under Knowledge Conflict
-
Debate with Images: Detecting Deceptive Behaviors in Multimodal Large Language Models
-
AdvJudge-Zero: Binary Decision Flips in LLM-as-a-Judge via Adversarial Control Tokens
-
Persuade Me if You Can: A Framework for Evaluating Persuasion Effectiveness and Susceptibility Among Large Language Models
-
VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models
-
When VLMs 'Fix' Students: Identifying and Penalizing Over-Correction in the Evaluation of Multi-line Handwritten Math OCR
-
MTLLFM: Multimodal-Temporal Laughter Localization: UR-FUNNY-Temporal and SMILE-Temporal Benchmarks with an Adaptive Multimodal Fusion Model
-
Depth Registers Unlock W4A4 on SwiGLU: A Reader/Generator Decomposition
-
When the Manual Lies: A Realistic Benchmark to Evaluate MCP Poisoning Attacks for LLM Agents
-
BC Protocol: Structured Dual-Expert Dialogue for Eliciting High-Quality Chain-of-Thought Post-Training Data
-
TempRet: Temporal Enhancement and Two-Stage Reranking for CVPR 2026 EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge
-
Geo-Expert: Towards Expert-Level Geological Reasoning via Parameter-Efficient Fine-Tuning
-
Quality-Conditioned Agreement in Automated Short Answer Scoring: Mid-Range Degradation and the Impact of Task-Specific Adaptation
-
Persona-Model Collapse in Emergent Misalignment
-
SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety
-
Graph Alignment Topology as an Inductive Bias for Grounding Detection
-
Structure-Guided Entity Resolution: Fine-Tuning LLMs for Robust Name Matching in Complex Linguistic Contexts
-
Co-ReAct: Rubrics as Step-Level Collaborators for ReAct Agents
-
Speak-to-Structure: Evaluating LLMs in Open-domain Natural Language-Driven Molecule Generation
-
Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training
-
Scam2Prompt: A Scalable Framework for Auditing Malicious Scam Endpoints in Production LLMs
-
Selective LoRA for Visual Tokens and Attention Heads
-
Beyond Public Access in LLM Pre-Training Data
-
OpenAI releases GPT-5.5 Instant, a new default model for ChatGPT
-
State Stream Transformer (SST) V2: Parallel Training of Nonlinear Recurrence for Latent Space Reasoning