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%).
792
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
-
Addressing Overthinking in Large Vision-Language Models via Gated Perception-Reasoning Optimization
GPRO trains a meta-controller on 790k failure-labeled samples to dynamically select fast, perception, or reasoning paths in LVLMs, yielding higher accuracy and shorter responses than prior slow-thinking methods.
-
AirNav: A Large-Scale UAV Vision-and-Language Navigation Dataset with Natural and Diverse Instructions
AirNav delivers a new 137K-sample UAV VLN benchmark with diverse natural instructions and reports AirVLN-R1 reaching 51.82% success on test-unseen data plus preliminary sim-to-real results.
-
Towards Fine-Grained and Multi-Granular Contrastive Language-Speech Pre-training
FCaps supplies 19M fine-grained speech style captions on 47k hours of audio via direct grounding, enabling the CLSP model to produce multi-granular representations that improve retrieval, zero-shot classification, and style scoring aligned with human judgments.
-
IBISAgent: Reinforcing Pixel-Level Visual Reasoning in MLLMs for Universal Biomedical Object Referring and Segmentation
IBISAgent enables MLLMs to perform iterative pixel-level visual reasoning for biomedical object referring and segmentation via text-based clicks and agentic RL, outperforming prior SOTA methods without model modifications.
-
DarkQA: Benchmarking Vision-Language Models on Visual-Primitive Question Answering in Low-Light Indoor Scenes
DarkQA is a new benchmark that measures vision-language model performance on basic visual questions under controlled low-light degradations modeled from real camera physics.
-
Style Amnesia: Investigating Speaking Style Degradation and Mitigation in Multi-Turn Spoken Language Models
Spoken language models exhibit style amnesia and fail to maintain instructed paralinguistic styles across multi-turn conversations, with explicit recall offering partial mitigation.
-
M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation
M³KG-RAG improves multimodal reasoning in large language models by constructing multi-hop knowledge graphs and selectively pruning retrieved context with GRASP.
-
dMLLM-TTS: Self-Verified and Efficient Test-Time Scaling for Diffusion Multi-Modal Large Language Models
dMLLM-TTS delivers up to 6x more efficient test-time scaling for diffusion MLLMs via O(N+T) hierarchical search and self-verified feedback, improving generation quality on GenEval across three models.
-
LangDriveCTRL: Natural Language Controllable Driving Scene Editing with Multi-modal Agents
LangDriveCTRL decomposes driving videos into 3D scene graphs and uses an agentic pipeline with specialized multi-modal agents to perform language-controlled object and behavior edits, achieving nearly 2x higher instruction alignment than prior state-of-the-art methods.
-
Dynamic Tool Dependency Retrieval for Lightweight Function Calling
DTDR dynamically retrieves relevant tools by modeling dependencies from demonstrations and conditioning on the evolving agent plan, improving function calling success rates by 23-104% over static retrievers across benchmarks.
-
4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation
4D-RGPT uses perceptual 4D distillation to boost region-level 4D perception in multimodal LLMs and reports gains on existing and new video QA benchmarks.
-
ART: Articulated Reconstruction Transformer
ART is a category-agnostic transformer that maps sparse multi-state RGB images to per-part 3D geometry, texture, and articulation parameters via learnable part slots.
-
ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body
ViBES introduces a speech-language-behavior model using modality-specific transformer experts that jointly generates dialogue and 3D body actions, showing gains over separate co-speech and text-to-motion baselines on multi-turn metrics.
-
VideoASMR-Bench: Can AI-Generated ASMR Videos Fool VLMs and Humans?
VideoASMR-Bench shows state-of-the-art VLMs fail to reliably detect AI-generated ASMR videos from real ones, though humans can still identify the fakes relatively easily.
-
Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space
DMLR performs dynamic visual-textual interleaving in latent space using confidence-guided latent policy gradient optimization and a dynamic visual injection strategy, yielding improved multimodal reasoning on benchmarks.
-
Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality
LivingSwap is the first video reference-guided face swapping model that uses keyframe conditioning and temporal stitching to preserve source video realism with high fidelity across long sequences.
-
Training Multi-Image Vision Agents via End2End Reinforcement Learning
IMAgent trains a multi-image vision agent via pure end-to-end RL with visual reflection tools and a two-layer motion trajectory masking strategy, reaching SOTA on single- and multi-image benchmarks while revealing tool-use effects on attention.
-
UniGeoSeg: Towards Unified Open-World Segmentation for Geospatial Scenes
UniGeoSeg releases the first million-scale dataset for instruction-driven remote sensing segmentation and a unified model that achieves state-of-the-art results with strong zero-shot generalization.
-
Can Multi-Modal LLMs Provide Live Step-by-Step Task Guidance?
Introduces the first dedicated benchmark for live multi-modal LLM task guidance with mistake detection and a streaming baseline model.
-
SpatialBench: Benchmarking Multimodal Large Language Models for Spatial Cognition
SpatialBench creates a five-level framework and 15-task benchmark to measure hierarchical spatial reasoning in MLLMs, finding strong basic perception but weak symbolic reasoning, causal inference, and planning.
-
Action Without Interaction: Probing the Physical Foundations of Video LMMs via Contact-Release Detection
Video LMMs name objects and actions reliably but fail to detect the precise frames and locations of contact and release events, revealing shortcut learning instead of physical grounding.
-
FinCriticalED: A Visual Benchmark for Financial Fact-Level OCR
FinCriticalED benchmark reveals that OCR and MLLM systems frequently fail to preserve critical financial facts such as numbers and monetary units even when lexical accuracy is high.
-
DeepEye-SQL: A Software-Engineering-Inspired Text-to-SQL Framework
DeepEye-SQL applies SDLC-inspired orchestration to Text-to-SQL, achieving 73.5% on BIRD-Dev, 75.07% on BIRD-Test, and 89.8% on Spider-Test with ~30B MoE models.
-
ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Calling
ToolPRM provides fine-grained intra-call process supervision via a new dataset and reward model, outperforming outcome and coarse-grained alternatives on function-calling benchmarks.
-
Exploring Cross-Modal Flows for Few-Shot Learning
FMA introduces flow matching for multi-step cross-modal feature alignment in few-shot learning, using fixed coupling, noise augmentation, and early-stopping to outperform one-step PEFT methods.
-
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents
SecureWebArena is a new benchmark suite for holistic security evaluation of LVLM-based web agents using diverse simulated environments, attack taxonomies, and multi-layered failure analysis across reasoning, behavior, and outcomes.
-
FinAuditing: A Financial Taxonomy-Structured Multi-Document Benchmark for Evaluating LLMs
FinAuditing is a taxonomy-structured multi-document benchmark with 1,102 instances averaging over 33k tokens from XBRL filings, defining three tasks to evaluate LLMs on financial auditing capabilities.
-
Beyond Classification Accuracy: Neural-MedBench and the Need for Deeper Reasoning Benchmarks
Neural-MedBench reveals sharp performance drops in state-of-the-art VLMs on reasoning-intensive neurology tasks compared to conventional classification benchmarks, with reasoning failures dominating errors.
-
MultiMat: Multimodal Program Synthesis for Procedural Materials using Large Multimodal Models
MultiMat shows multimodal large models plus constrained search produce higher-quality procedural material graphs than text-only baselines on a new production dataset.
-
Top-H Decoding: Adapting the Creativity and Coherence with Bounded Entropy in Text Generation
Top-H decoding is a computationally efficient greedy algorithm for an entropy-constrained mass maximization problem that improves the creativity-coherence trade-off over min-p sampling in LLM text generation.
-
GeoLaux: A Benchmark for Evaluating MLLMs' Geometry Performance on Long-Step Problems Requiring Auxiliary Lines
GeoLaux is a new benchmark of 2186 long-step geometry problems requiring auxiliary lines, used to evaluate 23 MLLMs and reveal major drops in performance on complex tasks.
-
OpenLifelogQA: An Open-Ended Multi-Modal Lifelog Question-Answering Dataset
Presents OpenLifelogQA, a new multimodal lifelog QA dataset with 14,187 pairs from 18 months of real-world data, plus baseline results on LLaVA-NeXT-Interleave.
-
MetaLint: Easy-to-Hard Generalization for Code Linting
MetaLint uses meta-learning to let models generalize from easy synthetic linting data to hard human-curated best practices, yielding large F-score gains on a new PEP-inspired benchmark.
-
Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models
Audio Flamingo 3 introduces an open large audio-language model achieving new state-of-the-art results on over 20 audio understanding and reasoning benchmarks using a unified encoder and curriculum training on open data.
-
High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning
MGPO elicits grounding in LMMs via multi-turn RL with binary rewards, yielding 5.4% and 5.2% gains on MME-Realworld and V* Bench and surpassing GPT-4o on the latter after training on 21K samples.
-
MMSearch-R1: Incentivizing LMMs to Search
MMSearch-R1 uses reinforcement learning to train multimodal models for on-demand multi-turn internet search with image and text tools, outperforming same-size RAG baselines and matching larger ones while cutting search calls by over 30%.
-
OSWorld-Human: Benchmarking the Efficiency of Computer-Use Agents
AI agents on OSWorld take 2.7-4.3 times more steps than human trajectories, with latency rising sharply due to repeated large model calls for planning and reflection.
-
LingoLoop Attack: Trapping MLLMs via Linguistic Context and State Entrapment into Endless Loops
LingoLoop traps MLLMs into generating up to 367 times more tokens by applying POS-aware attention adjustments to postpone EOS tokens and pruning generative paths to sustain repetitive loops.
-
ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving
ReCogDrive unifies VLM scene understanding with a diffusion planner reinforced by DiffGRPO to reach state-of-the-art results on NAVSIM and Bench2Drive benchmarks.
-
Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs
VISE is the first benchmark for sycophancy in Video-LLMs, with two training-free mitigation strategies based on key-frame selection and internal representation steering.
-
SIV-Bench: A Video Benchmark for Social Interaction Understanding and Reasoning
SIV-Bench is a new video benchmark with 2,792 clips and 5,455 QA pairs that evaluates MLLMs on social scene understanding, state reasoning, and dynamics prediction using social relation theory.
-
Rethinking Information Synthesis in Multimodal Question Answering A Multi-Agent Perspective
MAMMQA is a multi-agent framework that decomposes multimodal queries, retrieves modality-specific answers, performs cross-modal synthesis with VLMs, and integrates results via an LLM to outperform single-model baselines on QA benchmarks.
-
FinTagging: Benchmarking LLMs for Extracting and Structuring Financial Information
FinTagging decomposes XBRL tagging into FinNI extraction and FinCL full-taxonomy linking, showing LLMs handle extraction but struggle with fine-grained concept alignment in zero-shot settings.
-
MTR-Bench: A Comprehensive Benchmark for Multi-Turn Reasoning Evaluation
MTR-Bench is a new automated benchmark for multi-turn reasoning in LLMs covering diverse tasks and difficulty levels with 3600 instances.
-
Prompt Injection Attack to Tool Selection in LLM Agents
ToolHijacker optimizes malicious tool documents via a two-phase strategy to hijack LLM agents' tool selection in no-box settings.
-
Social Human Robot Embodied Conversation (SHREC) Dataset: Benchmarking Foundational Models' Social Reasoning
SHREC is a new benchmark dataset of embodied human-robot conversations that shows substantial performance gaps in state-of-the-art foundation models on tasks involving social error detection and rationale generation.
-
SpaceR: Reinforcing MLLMs in Video Spatial Reasoning
SpaceR uses a new verifiable dataset and map-imagination-augmented RLVR to reach SOTA spatial reasoning accuracy in MLLMs, exceeding GPT-4o on VSI-Bench.
-
Video-R1: Reinforcing Video Reasoning in MLLMs
Video-R1 uses temporal-aware RL and mixed datasets to boost video reasoning in MLLMs, with a 7B model reaching 37.1% on VSI-Bench and surpassing GPT-4o.
-
R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization
R1-VL uses StepGRPO with rule-based StepRAR and StepRVR rewards to let MLLMs learn step-by-step reasoning beyond imitation of positive paths.
-
Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation
Chain-of-thought monitoring detects reward hacking in frontier reasoning models, but strong optimization against the monitor produces obfuscated misbehavior that remains hard to detect.