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%).
774
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%.
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.
The paper delivers the first theoretical analysis and practical zeroth-order framework for algorithmic recourse under in-context learning for tabular prediction.
citing papers explorer
-
ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning
ResRL decouples shared semantics between positive and negative responses in LLM reinforcement learning via SVD-based projection residuals, outperforming baselines including NSR by up to 9.4% on math reasoning benchmarks.
-
FieryGS: In-the-Wild Fire Synthesis with Physics-Integrated Gaussian Splatting
FieryGS integrates LLM-based material reasoning, volumetric combustion simulation, and a unified renderer with 3D Gaussian Splatting to generate physically plausible and user-controllable fire in in-the-wild scenes.
-
Linguistically Informed Multimodal Fusion for Vietnamese Scene-Text Image Captioning: Dataset, Graph Framework, and Phonological Attention
Introduces ViTextCaps dataset and PhonoSTFG phonological graph fusion framework for Vietnamese scene-text image captioning, showing cross-modal graph edges harm performance.
-
Investigating More Explainable and Partition-Free Compositionality Estimation for LLMs: A Rule-Generation Perspective
A rule-generation perspective lets LLMs write programs as rules for data mapping and applies complexity theory to estimate their compositionality, tested on string-to-grid tasks.
-
Prefill-Time Intervention for Mitigating Hallucination in Large Vision-Language Models
Prefill-Time Intervention (PTI) reduces hallucinations in large vision-language models by applying a one-time modality-aware steering correction to the initial KV cache at the prefill stage rather than during autoregressive decoding.
-
SciEval: A Benchmark for Automatic Evaluation of K-12 Science Instructional Materials
SciEval is a new benchmark of expert-annotated K-12 science lessons for LLM-based automatic evaluation, where zero-shot models perform poorly but fine-tuning yields up to 11% gains.
-
Benchmarking Layout-Guided Diffusion Models through Unified Semantic-Spatial Evaluation in Closed and Open Settings
Introduces closed-set C-Bench and open-set O-Bench for layout-guided diffusion models, a unified semantic-spatial scoring protocol, and ranks six models after generating and evaluating 319,086 images.
-
AgentVisor: Defending LLM Agents Against Prompt Injection via Semantic Virtualization
AgentVisor cuts prompt injection success rate to 0.65% in LLM agents with only 1.45% utility loss via semantic privilege separation and one-shot self-correction.
-
PhysCodeBench: Benchmarking Physics-Aware Symbolic Simulation of 3D Scenes via Self-Corrective Multi-Agent Refinement
PhysCodeBench benchmark and SMRF multi-agent framework enable better AI generation of physically accurate 3D simulation code, boosting performance by 31 points over baselines.
-
Evaluating Temporal Consistency in Multi-Turn Language Models
Language models frequently violate temporal scope stability in multi-turn dialogues by drifting toward present-day assumptions even when they possess the correct facts.
-
Dr.Sai: An agentic AI for real-world physics analysis at BESIII
Dr.Sai autonomously executed full physics analysis pipelines on real BESIII data to re-measure ten J/psi decay branching fractions, matching established benchmarks without any manual coding.
-
Listening with Time: Precise Temporal Awareness for Long-Form Audio Understanding
LAT-Audio introduces a global-to-local reasoning approach with TWA-CoT that outperforms prior models on temporal tasks for audio up to 30 minutes.
-
PaperMind: Benchmarking Agentic Reasoning and Critique over Scientific Papers in Multimodal LLMs
PaperMind is a new benchmark that evaluates integrated multimodal reasoning and critique over scientific papers through four complementary task families across seven domains.
-
ParetoSlider: Diffusion Models Post-Training for Continuous Reward Control
ParetoSlider conditions diffusion models on continuous preference weights to approximate the full Pareto front, providing dynamic control over multi-objective rewards at inference time.
-
Exploring Spatial Intelligence from a Generative Perspective
Fine-tuning multimodal models on a new synthetic spatial benchmark improves generative spatial compliance on real and synthetic tasks and transfers to better spatial understanding.
-
SurgCoT: Advancing Spatiotemporal Reasoning in Surgical Videos through a Chain-of-Thought Benchmark
SurgCoT is a new benchmark that evaluates chain-of-thought spatiotemporal reasoning in multimodal large language models on surgical videos using five defined dimensions and an annotation protocol of Question-Option-Knowledge-Clue-Answer.
-
ReImagine: Rethinking Controllable High-Quality Human Video Generation via Image-First Synthesis
ReImagine decouples human appearance from temporal consistency via pretrained image backbones, SMPL-X motion guidance, and training-free video diffusion refinement to generate high-quality controllable videos.
-
ReflectMT: Internalizing Reflection for Efficient and High-Quality Machine Translation
ReflectMT internalizes reflection via two-stage RL to enable direct high-quality machine translation that outperforms explicit reasoning models like DeepSeek-R1 on WMT24 while using 94% fewer tokens.
-
Generative Texture Filtering
A two-stage fine-tuning strategy on pre-trained generative models enables effective texture filtering that outperforms prior methods on challenging cases.
-
STAR-Teaming: A Strategy-Response Multiplex Network Approach to Automated LLM Red Teaming
STAR-Teaming uses a Strategy-Response Multiplex Network inside a multi-agent framework to organize attack strategies into semantic communities, delivering higher attack success rates on LLMs at lower computational cost than prior methods.
-
MORPHOGEN: A Multilingual Benchmark for Evaluating Gender-Aware Morphological Generation
MORPHOGEN is a new multilingual benchmark for testing LLMs on gender-aware morphological generation via rewriting first-person sentences to the opposite gender in French, Arabic, and Hindi.
-
Denoise and Align: Diffusion-Driven Foreground Knowledge Prompting for Open-Vocabulary Temporal Action Detection
DFAlign uses diffusion-based denoising to generate foreground knowledge prompts that improve cross-modal alignment for detecting unseen actions in untrimmed videos, reporting state-of-the-art results on OV-TAD benchmarks.
-
Culture-Aware Humorous Captioning: Multimodal Humor Generation across Cultural Contexts
Introduces culture-aware humorous captioning task and staged alignment framework that improves contextual fit and balances image relevance with humor in multimodal LLMs.
-
How Creative Are Large Language Models in Generating Molecules?
Large language models exhibit distinct creative patterns in molecule generation, including higher constraint satisfaction when more constraints are added, and this is the first work to reframe molecule generation abilities as creativity.
-
BioVLM: Routing Prompts, Not Parameters, for Cross-Modality Generalization in Biomedical VLMs
BioVLM achieves state-of-the-art cross-modality generalization on biomedical VLMs by learning a prompt bank and routing inputs to the most discriminative prompts via low-entropy selection plus LLM distillation.
-
PBSBench: A Multi-Level Vision-Language Framework and Benchmark for Hematopathology Whole Slide Image Interpretation
PBS-VL trained on the new PBSInstr dataset outperforms general and pathology MLLMs on the PBSBench VQA tasks for hematopathology.
-
GaLa: Hypergraph-Guided Visual Language Models for Procedural Planning
GaLa uses hypergraph representations of objects and a TriView encoder with contrastive learning to improve vision-language models on procedural planning benchmarks.
-
LLMs can persuade only psychologically susceptible humans on societal issues, via trust in AI and emotional appeals, amid logical fallacies
LLMs persuade only psychologically susceptible humans on societal issues through trust in AI and emotional appeals, while both sides rely on logical fallacies in roughly one out of every six conversational turns.
-
From Tokens to Steps: Verification-Aware Speculative Decoding for Efficient Multi-Step Reasoning
SpecGuard adds step-level verification to speculative decoding via attention grounding and log-probability scores, yielding 3.6% higher accuracy and 11% lower latency on reasoning benchmarks.
-
Beyond Visual Cues: Semantic-Driven Token Filtering and Expert Routing for Anytime Person ReID
STFER uses LVLM-generated identity-consistent semantic text to drive visual token filtering and expert routing for improved any-time person re-identification under clothing changes and modality shifts.
-
ADAPT: Benchmarking Commonsense Planning under Unspecified Affordance Constraints
ADAPT augments planners with affordance reasoning to raise task success in environments with unspecified and time-varying object affordances, and a LoRA-finetuned VLM backend beats GPT-4o on the new DynAfford benchmark.
-
Chain of Modality: From Static Fusion to Dynamic Orchestration in Omni-MLLMs
Chain of Modality dynamically orchestrates multimodal input topologies and bifurcates cognitive execution to overcome static fusion biases in Omni-MLLMs.
-
ROSE: Retrieval-Oriented Segmentation Enhancement
ROSE is a retrieval-augmented plug-in that improves MLLM segmentation on novel and emerging entities by fetching web text and images and deciding when to use them.
-
Towards Unconstrained Human-Object Interaction
Introduces the U-HOI task and shows MLLMs plus a language-to-graph pipeline can handle human-object interactions without any predefined vocabulary at training or inference time.
-
ReviewGrounder: Improving Review Substantiveness with Rubric-Guided, Tool-Integrated Agents
ReviewGrounder decomposes review generation into rubric-guided drafting and tool-integrated grounding stages, outperforming larger baseline models on a new benchmark measuring alignment with human judgments and review quality.
-
ASTRA: Enhancing Multi-Subject Generation with Retrieval-Augmented Pose Guidance and Disentangled Position Embedding
ASTRA disentangles subject identity from pose structure in diffusion transformers via retrieval-augmented pose guidance, asymmetric EURoPE embeddings, and a DSM adapter to improve multi-subject generation.
-
GeoAgentBench: A Dynamic Execution Benchmark for Tool-Augmented Agents in Spatial Analysis
GeoAgentBench supplies a live execution environment and Plan-and-React architecture that lets tool-using AI agents handle multi-step GIS tasks more robustly than prior static evaluation methods.
-
Figma2Code: Automating Multimodal Design to Code in the Wild
The paper defines the Figma2Code task, releases a curated multimodal dataset from real Figma files, and benchmarks MLLMs to reveal that visual fidelity is achievable but responsive layouts and maintainable code remain weak.
-
The Impact of AI-Generated Text on the Internet
By mid-2025 roughly 35% of new websites are AI-generated or AI-assisted, correlating with lower semantic diversity and higher positive sentiment but showing no significant drop in factual accuracy or stylistic diversity.
-
FABLE: Fine-grained Fact Anchoring for Unstructured Model Editing
FABLE decouples fine-grained fact anchoring in shallow Transformer layers from deeper text generation to improve specific fact access while preserving holistic editing performance.
-
EgoEsportsQA: An Egocentric Video Benchmark for Perception and Reasoning in Esports
EgoEsportsQA is a new egocentric video QA benchmark from esports matches that shows state-of-the-art Video-LLMs reach only 71.58% accuracy and struggle more with tactical reasoning than basic perception.
-
HumDial-EIBench: A Human-Recorded Multi-Turn Emotional Intelligence Benchmark for Audio Language Models
HumDial-EIBench is a new benchmark using real human dialogues to evaluate audio language models on emotional intelligence tasks including multi-turn tracking, causal reasoning, empathy generation, and acoustic-semantic conflict resolution.
-
Scene Change Detection with Vision-Language Representation Learning
LangSCD fuses VLM-generated text descriptions with visual features and adds geometric-semantic matching to improve scene change detection, while releasing the NYC-CD dataset of 8122 New York City image pairs with multiclass annotations.
-
VidAudio-Bench: Benchmarking V2A and VT2A Generation across Four Audio Categories
VidAudio-Bench benchmarks V2A and VT2A models across four audio categories, revealing poor speech/singing performance and a tension between visual alignment and text instruction following.
-
TimeSeriesExamAgent: Creating Time Series Reasoning Benchmarks at Scale
TimeSeriesExamAgent combines templates and LLM agents to generate scalable time series reasoning benchmarks, demonstrating that current LLMs have limited performance on both abstract and domain-specific tasks.
-
Simulating Organized Group Behavior: New Framework, Benchmark, and Analysis
The paper introduces the Organized Group Behavior Simulation task, the GROVE benchmark with 8,052 real-world pairs, and a structured analytical framework with time-aware adapters that outperforms baselines on consistency and other metrics.
-
PilotBench: A Benchmark for General Aviation Agents with Safety Constraints
PilotBench reveals that LLMs follow safety instructions well in flight trajectory prediction but deliver lower numerical precision than traditional forecasters, exposing a precision-controllability tradeoff.
-
MolmoWeb: Open Visual Web Agent and Open Data for the Open Web
Open 4B and 8B visual web agents achieve state-of-the-art results on browser benchmarks by predicting actions from screenshots and instructions, outperforming similar open models and some closed larger-model agents, with full release of data and code planned.
-
Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces
Introduces OmniBehavior benchmark from real-world data and shows LLMs exhibit hyper-activity, persona homogenization, and utopian bias in behavior simulation.
-
InstAP: Instance-Aware Vision-Language Pre-Train for Spatial-Temporal Understanding
InstAP introduces instance-aware pre-training with a new dual-granularity dataset InstVL that improves both fine-grained instance retrieval and global video understanding over standard VLP baselines.