research

Revisiting Integration of Image and Metadata for DICOM Series Classification: Cross-Attention and Dictionary Learning

arXiv:2602.23833v2 Announce Type: replace-cross Abstract: Automated identification of DICOM image series is essential for large-scale medical image analysis, quality control, protocol harmonization, a

Research

RiT: Vanilla Diffusion Transformers Suffice in Representation Space

DGX agent

arXiv:2605.21981v1 Announce Type: new Abstract: Flow matching with x-prediction -- regressing the clean data point rather than the ambient velocity -- is known to exploit low-dimensional manifold stru

researcharxiv-cs-cv

22 May 2026

RobuQ: Pushing DiTs to W1.58A2 via Robust Activation Quantization

arXiv:2509.23582v2 Announce Type: replace Abstract: Diffusion Transformers (DiTs) have recently emerged as a powerful backbone for image generation, demonstrating superior scalability and performance

Robustness of breast lesion segmentation under MRI undersampling improves with k-space-aware deep learning

arXiv:2605.22327v1 Announce Type: new Abstract: Purpose: To assess whether breast lesion segmentation can be learned directly from acquired MRI k-space, and whether doing so improves robustness when d

Scene Abstraction for Lexical Semantics: Structured Representations of Situated Meaning

arXiv:2605.22542v1 Announce Type: new Abstract: Coffee and tea share many properties, yet they evoke strikingly different situations, atmospheres, and affective associations. These situated dimensions

SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformers

arXiv:2605.22668v1 Announce Type: new Abstract: Diffusion transformers (DiTs) have emerged as a dominant architecture for text-to-image generation, yet their performance drops when generating at resol

Sem-Detect: Semantic Level Detection of AI Generated Peer-Reviews

arXiv:2605.21713v1 Announce Type: new Abstract: How can we distinguish whether a peer review was written by a human or generated by an AI model? We argue that, in this setting, authorship should not b

Skarimva: Skeleton-based Action Recognition is a Multi-view Application

arXiv:2602.23231v2 Announce Type: replace Abstract: Human action recognition plays an important role when developing intelligent interactions between humans and machines. While there is a lot of activ

Slimmable ConvNeXt: Width-Adaptive Inference for Efficient Multi-Device Deployment

arXiv:2605.22677v1 Announce Type: new Abstract: Deploying vision models across devices with varying resource constraints, or even on a single device where available compute fluctuates due to battery s

SO-Mamba: State-Ownership Mamba for Unrolled MRI Reconstruction

arXiv:2605.22031v1 Announce Type: new Abstract: Accelerated MRI reconstruction requires recovering missing details while preserving anatomically coherent structures across large spatial regions. State

SPIRAL: Self-Evolving Action-Conditioned Video Generation via Reflective Planning Agents

arXiv:2603.08403v3 Announce Type: replace Abstract: Long-horizon action-conditioned video generation aims to synthesize temporally coherent videos that follow complex action instructions over extended

ST-SimDiff: Balancing Spatiotemporal Similarity and Difference for Efficient Video Understanding with MLLMs

arXiv:2605.22158v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) face significant computational overhead when processing long videos due to the massive number of visual token

stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation

arXiv:2605.21800v1 Announce Type: cross Abstract: World models are central to building agents that can reason, plan, and generalize beyond their training data. However, research on world models is cur

Swift Sampling: Selecting Temporal Surprises via Taylor Series

arXiv:2605.22678v1 Announce Type: new Abstract: While most frames in long-form video are redundant, the critical information resides in temporal surprises: moments where the actual visual features dev

Terminal Constraint Model Predictive Control for Image-Based Visual Servoing of UAVs with Kalman Filter-Based Moment Loss Compensation

arXiv:2605.22443v1 Announce Type: new Abstract: Image-Based Visual Servoing (IBVS) provides an efficient vision-guided control paradigm for unmanned aerial vehicles (UAVs) by directly regulating image

The Enhanced Games fit right in with the rest of 2026’s longevity vibes

This Sunday, a group of 42 athletes will gather in Las Vegas to compete in a somewhat unusual sporting competition. Participants in the inaugural Enhanced Games are being encouraged to take performanc

researchmit-tech-review

The Neglected Baseline in Model Interpretation

arXiv:2605.22417v1 Announce Type: new Abstract: We observe that existing model interpretation methods generally ignore the baseline, and such neglect often results in imprecise or even incorrect inter

This is rotten to the core. Howard Lutnick, the Commerce Secretary, cut a $5 million check to the Congressional Leadership Fund on April 1, …

This is rotten to the core. Howard Lutnick, the Commerce Secretary, cut a 5 million check to the Congressional Leadership Fund on April 1, just weeks after agreeing to testify before the House Oversig

researchyann-lecun--x

Time-varying rPPG signal separation via block-sparse signal model

arXiv:2605.22425v1 Announce Type: cross Abstract: Remote photoplethysmography (rPPG) enables non-contact measurement of cardiac pulse signals by analyzing subtle color changes in facial videos. Nevert

Token-weighted Direct Preference Optimization with Attention

arXiv:2605.21883v1 Announce Type: new Abstract: Direct Preference Optimization (DPO) aligns Large Language Models with human preferences without the need for a separate reward model. However, DPO trea

Tokenisation via Convex Relaxations

arXiv:2605.22821v1 Announce Type: new Abstract: Tokenisation is an integral part of the current NLP pipeline. Current tokenisation algorithms such as BPE and Unigram are greedy algorithms -- they make

Towards Initialization-free Calibrated Bundle Adjustment

arXiv:2506.23808v2 Announce Type: replace Abstract: A recent series of works has shown that initialization-free BA can be achieved using pseudo Object Space Error (pOSE) as a surrogate objective. The

Training-Free Fine-Grained Semantic Segmentations in Low Data Regimes: A FungiTastic Baseline

arXiv:2605.22492v1 Announce Type: new Abstract: Fine-grained semantic segmentation requires both precise localization and discrimination between visually similar classes. In FungiTastic, this problem

Translating Signals to Languages for sEMG-Based Activity Recognition

arXiv:2605.22403v1 Announce Type: new Abstract: Surface electromyography (sEMG) signal-based activity recognition has attracted increasing research attention in recent years. To develop accurate sEMG

TWINGS: Thin Plate Splines Warp-aligned Initialization for Sparse-View Gaussian Splatting

arXiv:2605.22069v1 Announce Type: new Abstract: Novel view synthesis from sparse-view inputs poses a significant challenge in 3D computer vision, particularly for achieving high-quality scene reconstr

Two-Stage Multimodal Framework for Emotion Mimicry Intensity Prediction

arXiv:2605.21869v1 Announce Type: new Abstract: We present our submission to the Hume-ABAW10 Emotional Mimicry Intensity (EMI) Challenge, which aims to predict six continuous emotion intensity dimensi

UIKA: Fast Universal Head Avatar from Pose-Free Images

arXiv:2601.07603v3 Announce Type: replace Abstract: We present UIKA, a feed-forward animatable Gaussian head model from an arbitrary number of pose-free inputs, including a single image, multi-view ca

Understanding Multimodal Failure in Action-Chunking Behavioral Cloning

arXiv:2605.22493v1 Announce Type: cross Abstract: Behavioral cloning becomes difficult when the same observation admits several valid actions. We study this problem for action-chunking policies and sh

Vendi Novelty Scores for Out-of-Distribution Detection

arXiv:2602.10062v2 Announce Type: replace-cross Abstract: Out-of-distribution (OOD) detection is critical for the safe deployment of machine learning systems. Existing post-hoc detectors typically rel

Video as Natural Augmentation: Towards Unified AI-Generated Image and Video Detection

arXiv:2605.21977v1 Announce Type: new Abstract: AI-generated content (AIGC) is rapidly improving, creating an urgent need for detectors that generalize across data sources, deployment pipelines, and v

Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning

arXiv:2601.23224v2 Announce Type: replace Abstract: Existing multimodal large language models for long-video understanding predominantly rely on uniform sampling and single-turn inference, limiting th

Virtual 3D H&E Staining from Phase-contrast Back-illumination Interference Tomography

arXiv:2605.22000v1 Announce Type: new Abstract: Three-dimensional (3D) histopathology of unprocessed tissues has the potential to transform disease management by enabling volumetric characterization o

VISTA: Validation-Guided Integration of Spatial and Temporal Foundation Models with Anatomical Decoding for Rare-Pathology VCE Event Detection -- after competition results

arXiv:2605.22096v1 Announce Type: new Abstract: Capsule endoscopy event detection is challenging because clinically relevant findings are sparse, visually heterogeneous, and evaluated at the event lev

VSAS-Bench: Real-Time Evaluation of Visual Streaming Assistant Models

researchapple-ml-research

Streaming vision-language models (VLMs) continuously generate responses given an instruction prompt and an online stream of input frames. This is a core mechanism for real-time visual assistants. Exis

We saw our first meaningful jump in the ARC-AGI-3 competition today @tufalabs went from 0.68% > 1.17% My notes: - .68% is the score of the b…

researchfrancois-chollet--x

We saw our first meaningful jump in the ARC-AGI-3 competition today @tufalabs went from 0.68% > 1.17% My notes: - .68% is the score of the best template (which is why so many people have this score) -

When Shared Knowledge Hurts: Spectral Over-Accumulation in Model Merging

arXiv:2602.05536v2 Announce Type: replace-cross Abstract: Model merging combines multiple fine-tuned models into a single model by adding their weight updates, providing a lightweight alternative to r

Whose Voice Counts? Mapping Stakeholder Perspectives on AI Through Public Submissions to the U.S. Government

arXiv:2605.22650v1 Announce Type: new Abstract: As artificial intelligence (AI) systems become more common in our daily lives, it is important to understand how different stakeholders comprehend and e

Zero-Shot Temporal Action Localization Through Textual Guidance

arXiv:2605.22201v1 Announce Type: new Abstract: Zero-shot temporal action localization (ZS-TAL) consists of classifying and localizing actions in untrimmed videos, where action classes are unseen at t

A Comprehensive Comparison of Deep Learning Architectures for COVID-19 Classification on CT & X-ray Imagery

arXiv:2605.20445v1 Announce Type: new Abstract: COVID-19 was a significant challenge that led to the loss of numerous lives daily. Not only a certain country was involved in this outbreak, but even th

A Dialogue between Causal and Traditional Representation Learning: Toward Mutual Benefits in a Unified Formulation

arXiv:2605.21058v1 Announce Type: new Abstract: Causal representation learning (CRL) and traditional representation learning have largely developed along different trajectories. Traditional representa

A Human-in-the-Loop Framework for Efficient Prompt Selection in Microscopy Vision-Language Models

arXiv:2605.20495v1 Announce Type: new Abstract: Deep-learning pipelines for microscopy image classification often require expensive, labor- and time-intensive expert annotation to produce high-quality

A Mechanistic Study of Tabular Foundation Models

arXiv:2605.21288v1 Announce Type: new Abstract: Tabular foundation models with different architectures converge in accuracy across a range of classification and regression tasks. This raises questions

A Non-Reference Diffusion-Based Restoration Framework for Landsat 7 ETM+ SLC-off Imagery in Antarctica

arXiv:2605.21371v1 Announce Type: new Abstract: Acquiring usable optical imagery in Antarctica is inherently challenging due to prolonged polar nights and frequent cloud cover. Landsat provides the lo

A Rigorous, Tractable Measure of Model Complexity

arXiv:2605.21167v1 Announce Type: cross Abstract: An accurate assessment of a model's complexity is crucial for topics such as interpretation, generalization, and model selection. However, most existi

A Sharper Picture of Generalization in Transformers

arXiv:2605.20988v1 Announce Type: new Abstract: We study transformers' generalization behavior on boolean domains from the perspective of the Fourier Spectra of their target functions. In contrast to

A Terrain-Adaptive epsilon-Constraint MPC for Uneven Terrain Kinodynamic Planning

arXiv:2605.21188v1 Announce Type: new Abstract: Kinodynamic planning for car-like vehicles on uneven terrain requires simultaneously optimizing competing objectives such as path efficiency and pose st

A Typed Tensor Language for Federated Learning

arXiv:2605.21103v1 Announce Type: new Abstract: Federated learning and analytics are often described as collections of separate protocols, even when they share the same mathematical form: client-local

Activation-Free Backbones for Image Recognition: Polynomial Alternatives within MetaFormer-Style Vision Models

arXiv:2605.20839v1 Announce Type: new Abstract: Modern vision backbones treat pointwise activations (e.g., ReLU, GELU) and exponential softmax as essential sources of nonlinearity, but we demonstrate