Introduces the TVR active viewpoint-matching task and TVRBench indoor simulation benchmark, where foundation models start at low single-digit success rates but reach 51.4% after visual-action SFT and multi-turn GRPO post-training.
super hub Mixed citations
GPT-4o System Card
Mixed citation behavior. Most common role is background (53%).
796
Pith papers citing it
Background
53% of classified citations
abstract
GPT-4o is an autoregressive omni model that accepts as input any combination of text, audio, image, and video, and generates any combination of text, audio, and image outputs. It's trained end-to-end across text, vision, and audio, meaning all inputs and outputs are processed by the same neural network. GPT-4o can respond to audio inputs in as little as 232 milliseconds, with an average of 320 milliseconds, which is similar to human response time in conversation. It matches GPT-4 Turbo performance on text in English and code, with significant improvement on text in non-English languages, while also being much faster and 50\% cheaper in the API. GPT-4o is especially better at vision and audio understanding compared to existing models. In line with our commitment to building AI safely and consistent with our voluntary commitments to the White House, we are sharing the GPT-4o System Card, which includes our Preparedness Framework evaluations. In this System Card, we provide a detailed look at GPT-4o's capabilities, limitations, and safety evaluations across multiple categories, focusing on speech-to-speech while also evaluating text and image capabilities, and measures we've implemented to ensure the model is safe and aligned. We also include third-party assessments on dangerous capabilities, as well as discussion of potential societal impacts of GPT-4o's text and vision capabilities.
hub tools
citation-role summary
background 97
baseline 51
method 23
dataset 3
citation-polarity summary
claims ledger
- abstract GPT-4o is an autoregressive omni model that accepts as input any combination of text, audio, image, and video, and generates any combination of text, audio, and image outputs. It's trained end-to-end across text, vision, and audio, meaning all inputs and outputs are processed by the same neural network. GPT-4o can respond to audio inputs in as little as 232 milliseconds, with an average of 320 milliseconds, which is similar to human response time in conversation. It matches GPT-4 Turbo performance on text in English and code, with significant improvement on text in non-English languages, while
authors
co-cited works
representative citing papers
VideoFDB is a new benchmark and LM-as-judge framework for evaluating full-duplex audio-visual-to-audio-visual conversational agents on nonverbal dynamics from real video calls.
M³Att poisons medical multimodal RAG by pairing covert textual misinformation with query-agnostic visual perturbations that increase retrieval of the bad content, causing LLMs to generate clinically plausible but incorrect responses.
MLLMs exhibit a Mirage effect by bypassing circuit diagrams in favor of header semantics for Verilog generation; VeriGround with identifier anonymization and D-ORPO training reaches 46% Functional Pass@1 while refusing blank images at >92%.
CHASM is a new benchmark dataset showing that existing multimodal large language models fail to reliably detect covert advertisements on Chinese social media even after fine-tuning.
HalluAudio is the first large-scale benchmark spanning speech, environmental sound, and music that uses human-verified QA pairs, adversarial prompts, and mixed-audio tests to measure hallucinations in large audio-language models.
EVE enables verifiable self-evolution of MLLMs by using a Challenger-Solver architecture to generate dynamic executable visual transformations that produce VQA problems with absolute execution-verified ground truth.
Harmful skills in open agent ecosystems raise average harm scores from 0.27 to 0.76 across six LLMs by lowering refusal rates when tasks are presented via pre-installed skills.
ReConText3D is the first replay-memory framework for continual text-to-3D generation that prevents catastrophic forgetting on new textual categories while preserving quality on previously seen classes.
MMRareBench provides 1,756 QA pairs and 7,958 images from PMC rare-disease cases to evaluate 23 MLLMs, revealing low treatment-planning scores and medical models underperforming general models on multi-image tasks due to capacity dilution.
DialBGM is a new benchmark dataset revealing that existing AI models fall far short of human performance when recommending fitting background music for open-domain conversations.
EgoSound is a new benchmark with 7315 QA pairs across seven tasks to evaluate egocentric sound understanding in multimodal large language models.
VLRS-Bench is the first benchmark dedicated to complex vision-language reasoning in remote sensing, with 2000 QA pairs across 14 tasks in cognition, decision, and prediction dimensions.
SwissGov-RSD is the first naturalistic cross-lingual document-level benchmark with human token-level semantic difference annotations, on which both LLMs and encoders show a large performance gap relative to simpler settings.
CritPt benchmark shows state-of-the-art LLMs reach only 5.7% average accuracy on full-scale unpublished physics research tasks, rising to about 10% with coding tools.
Flow-GRPO is the first online RL method for flow matching models, raising GenEval accuracy from 63% to 95% and text-rendering accuracy from 59% to 92% with little reward hacking.
Molmo VLMs trained on newly collected PixMo open datasets achieve state-of-the-art performance among open-weight models and surpass multiple proprietary VLMs including Claude 3.5 Sonnet and Gemini 1.5 Pro.
LiveBench is a contamination-limited LLM benchmark with auto-scored challenging tasks from recent sources across math, coding, reasoning and more, where top models score below 70%.
PhyEditBench is a new benchmark for physics-aware image editing with real and synthetic instances plus a training-free PhyWorld baseline that uses test-time scaling to outperform SOTA models.
CrypFormBench is a new benchmark jointly covering symbolic and computational security to evaluate LLMs on five formal analysis capabilities, with results showing top model Claude-3.5 scores 48.7/100 and most models struggling on generation, transformation, and correction.
SafeGen-Bench is a benchmark with 10 malicious categories that evaluates conditional T2V models on paired start frames and text prompts, finding unsafety scores up to 44.5 and 80% guardrail failure rate.
PolySpeech-100 is a new benchmark for native-level speech comprehension across 110 linguistic variants that evaluates 22 models and reports E2E advantages on dialects, robustness gaps on low-resource languages, and degradation from Chain-of-Thought prompting.
DeepLatent introduces a parallel latent visual reasoning framework with learnable 2D tokens and continuous RL, trained via distillation then RL, plus a new 180K dataset, claiming SOTA benchmark results.
SelSkill applies dual-granularity preference learning to selective skill-or-skip decisions, improving task success by 10.9 points and execution precision by 29.1 points on ALFWorld with Qwen3-8B.
citing papers explorer
-
LiteGUI: Distilling Compact GUI Agents with Reinforcement Learning
LiteGUI trains 2B/3B-scale GUI agents via SFT-free guided on-policy distillation and multi-solution dual-level GRPO to reach SOTA lightweight performance and compete with larger models.
-
SEIF: Self-Evolving Reinforcement Learning for Instruction Following
SEIF creates a self-reinforcing loop in which an LLM alternately generates increasingly difficult instructions and learns to follow them better using reinforcement learning signals from its own judgments.
-
EditTransfer++: Toward Faithful and Efficient Visual-Prompt-Guided Image Editing
EditTransfer++ delivers state-of-the-art faithfulness to visual editing examples and faster inference by removing text conditioning during fine-tuning and applying best-worst contrastive refinement plus condition compression.
-
Learning Agent Routing From Early Experience
BoundaryRouter routes queries to LLM or agent using early experience memory from a seed set, cutting inference time 60.6% versus always using agents and raising performance 28.6% versus always using direct LLM inference.
-
HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents
HyperEyes presents a parallel multimodal search agent using dual-grained efficiency-aware RL with a new TRACE reward and IMEB benchmark, claiming 9.9% higher accuracy and 5.3x fewer tool calls than prior open-source agents.
-
SHARP: A Self-Evolving Human-Auditable Rubric Policy for Financial Trading Agents
SHARP is a neuro-symbolic method that evolves bounded, auditable rule rubrics for LLM trading agents via cross-sample attribution and walk-forward validation, raising compact-model performance by 10-20 percentage points across equity sectors.
-
BAMI: Training-Free Bias Mitigation in GUI Grounding
BAMI mitigates precision and ambiguity biases in GUI grounding via coarse-to-fine focus and candidate selection, raising accuracy on ScreenSpot-Pro without training.
-
Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key
RL training compute for logical reasoning follows a power law with horizon depth whose exponent rises with logical expressiveness, yielding better downstream transfer when models train on richer logics.
-
Continuous Latent Diffusion Language Model
Cola DLM proposes a hierarchical latent diffusion model that learns a text-to-latent mapping, fits a global semantic prior in continuous space with a block-causal DiT, and performs conditional decoding, establishing latent prior modeling as an alternative to token-level autoregressive language model
-
A Versatile AI Agent for Rare Disease Diagnosis and Risk Gene Prioritization
Hygieia is a new AI agent system that integrates phenotypes, genetics, and records to achieve superior rare disease diagnosis and gene prioritization with confidence scores.
-
IRC-Bench: Recognizing Entities from Contextual Cues in First-Person Reminiscences
IRC-Bench is a new dataset and evaluation framework for implicit entity recognition in reminiscence narratives, where entities must be inferred from non-local contextual cues across 1,994 transcripts linked to 12,337 WikiData entities.
-
MSD-Score: Multi-Scale Distributional Scoring for Reference-Free Image Caption Evaluation
MSD-Score introduces multi-scale distributional scoring on von Mises-Fisher mixtures to evaluate image captions without references and reports state-of-the-art correlation with human judgments.
-
Milestone-Guided Policy Learning for Long-Horizon Language Agents
BEACON uses milestone partitioning, temporal reward shaping, and dual-scale advantage estimation to nearly double success rates on long-horizon ALFWorld tasks while raising effective sample use from 23.7% to 82%.
-
Think, then Score: Decoupled Reasoning and Scoring for Video Reward Modeling
DeScore decouples CoT reasoning from reward scoring in video reward models using a two-stage training process to improve generalization and avoid optimization bottlenecks of coupled generative RMs.
-
VideoRouter: Query-Adaptive Dual Routing for Efficient Long-Video Understanding
VideoRouter uses dual semantic and image routers for query-adaptive token compression in long-video models, delivering up to 67.9% reduction while outperforming the InternVL baseline on VideoMME, MLVU, and LongVideoBench.
-
LoopTrap: Termination Poisoning Attacks on LLM Agents
LoopTrap is an automated red-teaming framework that crafts termination-poisoning prompts to amplify LLM agent steps by 3.57x on average (up to 25x) across 8 agents.
-
MUSE: Resolving Manifold Misalignment in Visual Tokenization via Topological Orthogonality
MUSE decouples reconstruction and semantic learning in visual tokenization via topological orthogonality, yielding SOTA generation quality and improved semantic performance over its teacher model.
-
Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe
Uni-OPD unifies on-policy distillation across LLMs and MLLMs with dual-perspective strategies that promote student exploration and enforce order-consistent teacher supervision based on outcome rewards.
-
Replacing Parameters with Preferences: Federated Alignment of Heterogeneous Vision-Language Models
MoR lets clients train local reward models on private preferences and uses a learned Mixture-of-Rewards with GRPO on the server to align a shared base VLM without exchanging parameters, architectures, or raw data.
-
Chart-FR1: Visual Focus-Driven Fine-Grained Reasoning on Dense Charts
Chart-FR1 uses Focus-CoT for linking reasoning to visual cues and Focus-GRPO reinforcement learning with efficiency rewards to outperform prior MLLMs on dense chart reasoning tasks.
-
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety
MultiBreak is a large diverse multi-turn jailbreak benchmark that achieves substantially higher attack success rates on LLMs than prior datasets and reveals topic-specific vulnerabilities in multi-turn settings.
-
ClarifySTL: An Interactive LLM Agent Framework for STL Transformation through Requirements Clarification
ClarifySTL uses LLM agents to interactively detect and resolve vagueness and ambiguity in natural language requirements via clarification queries before generating STL formulas, with evaluations on existing and new benchmarks showing effectiveness.
-
EmoMM: Benchmarking and Steering MLLM for Multimodal Emotion Recognition under Conflict and Missingness
EmoMM benchmark reveals Video Contribution Collapse in MLLMs for emotion recognition under modality conflict and missingness, mitigated by CHASE head-level attention steering.
-
CleanBase: Detecting Malicious Documents in RAG Knowledge Databases
CleanBase identifies malicious documents in RAG databases by detecting cliques in a semantic similarity graph constructed using embedding models and a statistical threshold.
-
Relation Reasoning with LLMs in Expensive Optimization
R2SAEA fine-tunes an LLM with RL to reason about solution relations for surrogate-assisted evolutionary optimization, reporting improved relation prediction and SOTA performance on single- and multi-objective benchmarks.
-
METASYMBO: Multi-Agent Language-Guided Metamaterial Discovery via Symbolic Latent Evolution
MetaSymbO proposes a three-agent framework with symbolic latent evolution that improves structural validity and language alignment for metamaterial design from free-form text intents.
-
World2VLM: Distilling World Model Imagination into VLMs for Dynamic Spatial Reasoning
Distilling view-consistent future views and action-outcome supervision from a generative world model into a VLM via two-stage post-training improves dynamic spatial reasoning on SAT-Real, VSI-Bench and similar benchmarks while avoiding test-time world-model cost.
-
Breaking Bad Financial Habits: How LLM Conversations Correct Financial Misconceptions
Purposefully designed LLM conversations durably correct financial misconceptions when they include corrective intent and match the recipient's level of financial knowledge.
-
DenseStep2M: A Scalable, Training-Free Pipeline for Dense Instructional Video Annotation
A scalable training-free pipeline using video segmentation, filtering, and off-the-shelf multimodal models creates DenseStep2M, a dataset of 100K videos and 2M detailed instructional steps that improves dense captioning, step grounding, and cross-modal retrieval.
-
Multiple Consistent 2D-3D Mappings for Robust Zero-Shot 3D Visual Grounding
MCM-VG achieves state-of-the-art zero-shot 3D visual grounding on ScanRefer and Nr3D by creating consistent 2D-3D mappings across semantic, geometric, and viewpoint dimensions using LLMs and VLMs.
-
Refinement via Regeneration: Enlarging Modification Space Boosts Image Refinement in Unified Multimodal Models
Refinement via Regeneration (RvR) reformulates image refinement in unified multimodal models as conditional regeneration using prompt and semantic tokens from the initial image, yielding higher alignment scores than editing-based methods.
-
PhysNote: Self-Knowledge Notes for Evolvable Physical Reasoning in Vision-Language Model
PhysNote lets VLMs externalize physical knowledge into hierarchical self-generated notes, stabilizing spatio-temporal reasoning and yielding 56.68% accuracy on PhysBench with a 4.96% gain over the best multi-agent baseline.
-
MEMCoder: Multi-dimensional Evolving Memory for Private-Library-Oriented Code Generation
MEMCoder boosts LLM code generation for private libraries by 16.31% pass@1 via a multi-dimensional evolving memory that distills usage guidelines from execution feedback and combines them with static docs.
-
Exploring Audio Hallucination in Egocentric Video Understanding
AV-LLMs hallucinate audio from visuals in egocentric videos, scoring only 27.3% accuracy on foreground sounds and 39.5% on background sounds in a 1000-question evaluation.
-
LLMs Reading the Rhythms of Daily Life: Aligned Understanding for Behavior Prediction and Generation
BUA aligns LLMs to behavior data via sequence embeddings and a three-stage curriculum, outperforming prior methods on prediction and generation in two real-world datasets.
-
Optimal Question Selection from a Large Question Bank for Clinical Field Recovery in Conversational Psychiatric Intake
An LLM-guided adaptive policy outperforms fixed clinical intake forms and random questioning at recovering target information from synthetic psychiatric patients in 300 simulated sessions.
-
BioMiner: A Multi-modal System for Automated Mining of Protein-Ligand Bioactivity Data from Literature
BioMiner introduces a multi-modal extraction system and BioVista benchmark that achieves F1 0.32 on bioactivity triplets and demonstrates utility in scaling datasets and improving QSAR models.
-
HiCrew: Hierarchical Reasoning for Long-Form Video Understanding via Question-Aware Multi-Agent Collaboration
HiCrew improves long-form video question answering on EgoSchema and NExT-QA via a hybrid tree for temporal topology, question-aware captioning, and adaptive multi-agent planning, with gains in temporal and causal reasoning.
-
Using Machine Mental Imagery for Representing Common Ground in Situated Dialogue
Incremental visual scaffolding using multimodal models improves persistent common ground representation in situated dialogue by reducing representational blur compared to text-only approaches, with hybrid text-visual yielding best results on the IndiRef benchmark.
-
OMIBench: Benchmarking Olympiad-Level Multi-Image Reasoning in Large Vision-Language Model
OMIBench benchmark reveals that current LVLMs achieve at most 50% on Olympiad problems requiring reasoning across multiple images.
-
MGDA-Decoupled: Geometry-Aware Multi-Objective Optimisation for DPO-based LLM Alignment
MGDA-Decoupled applies geometry-based multi-objective optimization within the DPO framework to find shared descent directions that account for each objective's convergence dynamics, yielding higher win rates on UltraFeedback.
-
Evaluating Assurance Cases as Text-Attributed Graphs for Structure and Provenance Analysis
Graph neural networks on assurance case graphs reach 0.76 ROC-AUC for link prediction and 0.94 F1 for distinguishing human from LLM-generated cases, with observed differences in hierarchical linking patterns.
-
Video-ToC: Video Tree-of-Cue Reasoning
Video-ToC adds tree-guided cue localization, demand-based RL rewards, and automated datasets to video LLMs, reporting better results than prior methods on six understanding benchmarks plus a hallucination test.
-
WebGen-R1: Incentivizing Large Language Models to Generate Functional and Aesthetic Websites with Reinforcement Learning
WebGen-R1 uses end-to-end RL with scaffold-driven generation and cascaded rewards for structure, function, and aesthetics to transform a 7B model into a generator of deployable multi-page websites that rivals much larger models.
-
Mol-Debate: Multi-Agent Debate Improves Structural Reasoning in Molecular Design
Mol-Debate applies multi-agent debate in an iterative loop with perspective orchestration to achieve state-of-the-art text-guided molecular design, scoring 59.82% exact match on ChEBI-20 and 50.52% weighted success on S2-Bench.
-
Visual Reasoning through Tool-supervised Reinforcement Learning
ToolsRL trains MLLMs via a tool-specific then accuracy-focused RL curriculum to master visual tools for complex reasoning tasks.
-
SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models
SafetyALFRED shows multimodal LLMs recognize kitchen hazards accurately in QA tests but achieve low success rates when required to mitigate those hazards through embodied planning.
-
If you're waiting for a sign... that might not be it! Mitigating Trust Boundary Confusion from Visual Injections on Vision-Language Agentic Systems
LVLM-based agents exhibit trust boundary confusion with visual injections and a multi-agent defense separating perception from decision-making reduces misleading responses while preserving correct ones.
-
Reasoning Structure Matters for Safety Alignment of Reasoning Models
Changing the internal reasoning structure of large reasoning models through simple supervised fine-tuning on 1K examples produces strong safety alignment that generalizes across tasks and languages.
-
How Adversarial Environments Mislead Agentic AI?
Adversarial compromise of tool outputs misleads agentic AI via breadth and depth attacks, revealing that epistemic and navigational robustness are distinct and often trade off against each other.