Stanford HAI

Packed trajectories, not sequential rollouts, unlock high-fidelity multi-turn image editing by preventing visual drift.

Standard motion benchmarks fail inside the cabin because drivers mostly sit still—until right before a maneuver, when arm movement spikes 3.4x.

ToPO achieves superior image generation performance by optimizing token-conditioned preferences, outperforming existing methods across multiple evaluation metrics.

AnaDiffusion allows for precise and controllable editing of 3D brain MRIs, achieving the lowest FID scores while preserving anatomical integrity.

EmoScope redefines emotional image editing by enabling users to discover unique, context-specific editing strategies rather than relying on static templates.

FIDAC reveals how interpersonal distance can be accurately quantified from video, transforming facial detection data into actionable insights.

Radiological findings in frozen vision-language models are encoded by just 10 channels, revealing a surprising efficiency that challenges traditional assumptions about model complexity.

Achieving a staggering 250,000x speedup in hologram synthesis without compromising image quality could redefine the future of 3D display technologies.

BrainNext achieves top-tier performance in neuroimaging tasks by leveraging self-supervised learning on a massive dataset, highlighting the power of large-scale pretraining in medical applications.

Hierarchy-aware training combined with anatomy-guided learning boosts LUS video classification accuracy while enhancing model interpretability.

Systematic misalignments in MLLM-generated captions can be detected with 63.8% accuracy, revealing a critical flaw in image-text pairing that has been largely overlooked.

A novel AI-driven approach reveals that targeted facial stimuli can significantly enhance the detection of perceptual differences between autistic and neurotypical individuals.

FourTune slashes memory overhead by 2.25x while matching the performance of full-precision fine-tuning in diffusion models.

Achieving state-of-the-art 4D reconstruction, this method transforms monocular videos into high-quality dynamic 3D representations, even in challenging conditions.

Current AI models miss critical tumor detections in underrepresented demographics, revealing a hidden bias that could compromise patient outcomes.

Current visual world models show a dramatic decline in performance when faced with unconventional and impossible physical interactions, highlighting a critical gap in their generalization capabilities.

FlowObject bridges the gap between generative priors and real-world observations, achieving unprecedented fidelity in 3D reconstruction from sparse views.

Achieving a dual-purpose tokenizer that excels in both clinical task performance and controllable 3D brain MRI generation could revolutionize how we approach medical imaging.

PermaVid achieves unprecedented long-term consistency in video generation, even after significant edits, by intelligently disentangling appearance and geometry in memory.

ProTrans reveals that modeling disease progression as directional semantic transitions can dramatically enhance the interpretability and accuracy of longitudinal chest X-ray analysis.

Action-conditioned predictions from a compact latent model reveal that diffusion methods can dramatically outperform traditional regression in scene forecasting for autonomous vehicles.

Traditional diffusion models fail to capture temporal dependencies, but this new framework generates realistic sequential data without anticipating future information.

Task-aware foveated imaging can dramatically improve visual perception performance while operating within severe bandwidth limitations.

Unlock linear-time video VLMs without accuracy loss: StateKV matches full self-attention while crushing sliding-window methods, all without finetuning.

Forget hand-crafted physics models – NeuROK learns to generate realistic object deformations directly from data, opening the door to more general and scalable 4D simulations.

VideoLLMs are surprisingly bad at keeping track of who did what, frequently mixing up actions across different video segments like a confused movie editor.

Stop throwing away information: Listwise preference optimization extracts more signal from multi-candidate image datasets and continuous reward scores, boosting diffusion model alignment beyond pairwise methods.

Substrate choice dictates tin anode morphology and stability in aqueous batteries, enabling a 70% utilization anode with extended lifespan.

Current video generation benchmarks miss the forest for the trees: EvalVerse actually measures cinematic quality, not just prompt adherence.

Instead of training separate video diffusion models for each multimodal task, UniVidX learns a single model that handles diverse pixel-aligned video generation problems.

Forget noisy starts – ABC diffusion models leverage the inherent structure of continuous processes, generating future states from already-close previous states for more realistic dynamics.

Generate navigable, 3D-consistent simulations of real-world locations with arbitrary weather and dynamic object configurations using only geo-registered video data.

Achieve real-time video understanding with transparent reasoning: \model{} aligns response timing with visual evidence, offering a breakthrough for online video LLMs.

RadAgent doesn't just give you the answer; it shows its work, offering clinicians a transparent, step-by-step reasoning trace for AI-generated CT reports.

Neural video codecs can be designed for biological substrates from the ground up, unlocking a new paradigm for DNA storage.

Scaling robot learning with human data isn't a simple "more is better" equation; alignment with robot learning objectives is key.

Unlock interactive digital twins from messy, real-world videos: FunRec automatically turns egocentric RGB-D recordings into simulation-ready 3D scenes.

Music-grounded video editing can now produce significantly more coherent timelines thanks to a novel global-local coordination mechanism that resolves cross-segment conflicts.

Ditch the anchors and NMS: AutoReg3D reimagines 3D object detection as a sequence generation problem, opening the door for language-model techniques in 3D perception.

Ditch the training overhead and still get up to 4.79x faster diffusion sampling with Spectrum, a training-free feature forecasting method that actually maintains image quality.

By unifying hand motion estimation and generation into a single diffusion framework, UniHand handles heterogeneous inputs and challenging conditions like occlusions better than task-specific models.

Robots can now navigate complex outdoor environments and find objects using natural language queries, even without prior maps or precise depth sensing.

Achieve spatially faithful image-to-image translation without cross-domain supervision by bridging diffusion models with self-supervised semantic representations.

Verification at test time can be a surprisingly effective alternative to scaling policy learning for vision-language-action alignment, yielding substantial gains in both simulated and real-world robotic tasks.