Scalable GANs with Transformers
arXiv:2509.24935v2 Announce Type: replace-cross Abstract: Scalability has driven recent advances in generative modeling, yet its principles remain underexplored for adversarial learning. We investigat
Knowledge catalogue
arXiv:2509.24935v2 Announce Type: replace-cross Abstract: Scalability has driven recent advances in generative modeling, yet its principles remain underexplored for adversarial learning. We investigat
arXiv:2509.26619v3 Announce Type: replace-cross Abstract: Many static benchmarks are beginning to saturate: as models rapidly improve, they achieve near-perfect scores on fixed test sets, leaving litt
arXiv:2506.07813v2 Announce Type: replace-cross Abstract: Arbitrary-scale image super-resolution aims to upsample images to any desired resolution, offering greater flexibility than traditional fixed-
arXiv:2605.26744v1 Announce Type: new Abstract: Human motion generation has made tremendous progress in recent years, with state-of-the-art approaches surpassing ground truth data in leading evaluatio
arXiv:2601.04275v2 Announce Type: replace-cross Abstract: Machine unlearning aims to selectively remove the influence of specific training samples to satisfy privacy regulations such as the GDPR's 'Ri
arXiv:2605.26295v1 Announce Type: new Abstract: Accurate classification of sleep stages is crucial for diagnosing sleep disorders and automating this process can significantly enhance clinical assessm
arXiv:2605.26428v1 Announce Type: new Abstract: Generating high-quality, pedagogically useful questions from lecture slide decks is difficult because important instructional content is distributed acr
arXiv:2605.26884v1 Announce Type: new Abstract: In this paper, we address the problem of detecting small, dense, and overlapping objects, a major challenge in computer vision. Our focus is on reviewin
arXiv:2605.27075v1 Announce Type: new Abstract: Diffusion Transformers (DiTs) achieve strong visual quality, but their iterative denoising process requires many costly Transformer evaluations. Trainin
arXiv:2605.26456v1 Announce Type: new Abstract: Sparse-LiDAR-prompted depth foundation models (PromptDA, Prior Depth Anything, DMD3C) have shown strong results on indoor scenes or within KITTI's stand
arXiv:2605.26900v1 Announce Type: new Abstract: A fundamental open question in self-supervised learning (SSL) is the explicit characterization of the optimal geometry of the learned representations. R
arXiv:2605.26733v1 Announce Type: cross Abstract: Looped Language Models (LoopLMs) enable efficient latent reasoning through depth recurrence, yet exhibit unreliable test-time scaling behavior: perfor
arXiv:2602.09842v2 Announce Type: replace-cross Abstract: We present a theoretical analysis of stochastic optimization methods in terms of their sensitivity with respect to the step size. We identify
arXiv:2605.26429v1 Announce Type: cross Abstract: This paper addresses structured out-of-distribution (OOD) testing in high-stakes machine learning applications. Traditional conformal methods rely on
arXiv:2601.06580v2 Announce Type: replace Abstract: Singlish is a creole rooted in Singapore's multilingual environment that continues to evolve alongside social and technological change. We examine d
arXiv:2511.04711v2 Announce Type: replace-cross Abstract: Large-scale vision-language models, especially CLIP, have demonstrated remarkable performance across diverse downstream tasks. Soft prompts, a
arXiv:2605.27245v1 Announce Type: new Abstract: Symbolic regression (SR) seeks closed-form mathematical expressions that fit observed data. Neural SR methods amortize the search by training an encoder
arXiv:2510.04533v2 Announce Type: replace Abstract: Diffusion models achieve state-of-the-art image generation but often produce semantic inconsistencies, or hallucinations. Existing inference-time gu
arXiv:2605.26628v1 Announce Type: new Abstract: This report describes Tail-Aware HiFloat4, our submission to the low-bit text-to-video generation quantization challenge. Our method adapts the public V
arXiv:2504.02775v2 Announce Type: replace Abstract: We aim to solve unsupervised anomaly detection in a practical challenging environment where the normal dataset is both contaminated with defective r
arXiv:2605.26436v1 Announce Type: cross Abstract: Discrete masked diffusion language models such as LLaDA generate text through iterative denoising, where mask tokens are progressively replaced with p
arXiv:2605.27167v1 Announce Type: new Abstract: Planning the motion path for a tightly coupled dual-arm space manipulator under closed-chain constraints is a fundamental yet challenging problem in on-
arXiv:2605.25538v2 Announce Type: replace Abstract: Track materialization converts raw video into reusable object tracks that downstream queries can run against without rerunning tracking, but extract
arXiv:2605.26778v1 Announce Type: new Abstract: Retrieval-augmented generation promises to ground language model outputs in external evidence, yet the field has no reliable way to verify whether retri
arXiv:2605.26346v1 Announce Type: new Abstract: Objective: To describe the design and early clinical evaluation of The Daily Dose (TDD), an LLM-driven, automated clinical summarization and clinical-tr
This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. Stay on top of what’s going on in AI this summer Here at MIT T
today was a massive day for protein engineering. esmfold2 dropped—next gen of the esm series, fully open on @huggingscience. 1.1 billion predicted structures, 6.8 billion sequences. 800m more entries
arXiv:2605.27154v1 Announce Type: new Abstract: While rule-based reinforcement learning has recently catalyzed explicit reasoning in multimodal models, tactile reasoning remains largely underexplored.
arXiv:2605.26958v1 Announce Type: cross Abstract: Reinforcement learning in open-ended long-form generation is challenging because reliable reference answers and automatic metrics are often unavailabl
arXiv:2605.27343v1 Announce Type: new Abstract: Diffusion models have emerged as powerful tools for high-quality image generation and editing, but guiding these models to produce specific outputs rema
arXiv:2605.27180v1 Announce Type: new Abstract: Volcanoes emit large amounts of CO2, directly influencing human lives. Mapping volcanic gas emissions helps to forecast eruptions and understand the imp
arXiv:2605.26991v1 Announce Type: new Abstract: Collaboration is central to human behavior, enabling tasks beyond individual capability. This ability arises from coordinating actions through internal
arXiv:2605.27033v1 Announce Type: cross Abstract: Transformer-based large language models (LLMs) are comprised of billions of parameters arranged in deep and wide computational graphs, but it is not c
arXiv:2605.26576v1 Announce Type: new Abstract: Referring 3D Gaussian Splatting (R3DGS), which utilizes natural language for 3D object segmentation, has emerged as a crucial capability for embodied AI
arXiv:2512.06609v3 Announce Type: replace-cross Abstract: Vector-quantized variational autoencoders (VQ-VAEs) are discrete autoencoders that compress images into discrete tokens. However, they are dif
arXiv:2605.27269v1 Announce Type: new Abstract: Disease forecasting models typically rely on a single data stream, making models brittle when histories are short or noisy. Recent top-performing models
Trump could have presided over a very strong economy. All he had to do was...nothing: Inflation was trending downward, the AI boom was raising growth. Instead, he engineered a global trade war and ene
Trump is now 'the most unpopular president since our poll started in 2009. His net approval rating is -24,' due to his war of choice in Iran and his mishandling of the economy. https://trib.al/G1c4KcW
arXiv:2605.26161v1 Announce Type: cross Abstract: Time series foundation models (TSFMs) are increasingly pretrained on large corpora, raising concerns that evaluation datasets may have been exposed du
arXiv:2605.27205v1 Announce Type: cross Abstract: Wireless digital twins require repeated synchronization between a time-evolving physical scene and its digital counterpart under limited and time-vary
arXiv:2605.27078v1 Announce Type: cross Abstract: Training loss and accuracy are the standard signals used to monitor generalization during deep neural network training. Two well-documented phenomena
arXiv:2605.26849v1 Announce Type: new Abstract: Sampling multiple responses improves language model reasoning, but uniform compute allocation is inefficient: easy questions are over-sampled while hard
arXiv:2603.23994v2 Announce Type: replace-cross Abstract: Generative optimization uses large language models (LLMs) to iteratively improve artifacts (such as code, workflows or prompts) using executio
arXiv:2605.26248v1 Announce Type: cross Abstract: We present a functional form (that we refer to as a Unified Neural Scaling Law (UNSL)) that accurately models and extrapolates the scaling behaviors o
arXiv:2605.26368v1 Announce Type: cross Abstract: Geometry estimation from perspective images has greatly advanced, maturing to the point where off-the-shelf foundation models are able to reconstruct
arXiv:2605.27139v1 Announce Type: cross Abstract: Electron tomography (ET) plays an important role in the three-dimensional (3D) characterization of nanomaterials. However, under limited-angle and spa
arXiv:2312.02694v2 Announce Type: replace Abstract: Existing optical character recognition (OCR) methods rely on task-specific designs with divergent paradigms, architectures, and training strategies,
arXiv:2602.21450v2 Announce Type: replace Abstract: Many robotic systems allow independent control of position and orientation (pose), including omnidirectional aerial vehicles, underwater robots, and
arXiv:2605.26498v1 Announce Type: new Abstract: Large language models (LLMs) have improved Verilog generation from natural-language specifications, but most pipelines still treat generation as isolate
arXiv:2605.26350v1 Announce Type: cross Abstract: In-context learning (ICL) is often motivated by the intuition that demonstrations help because they provide correct input-output examples. However, we
arXiv:2605.27313v1 Announce Type: new Abstract: Demographic information is often used to model annotator perspectives in subjective tasks such as hate speech detection, but its benefit is inconsistent
arXiv:2605.26929v1 Announce Type: new Abstract: Adversarial training (AT) remains one of the most reliable empirical defenses against adversarial attacks. Its robustness critically depends on how the
arXiv:2605.26171v1 Announce Type: new Abstract: Many practical anomalies are not merely rare inputs, but violations of semantic constraints: objects co-occur in structured ways, actions imply precondi
arXiv:2605.24906v2 Announce Type: replace Abstract: Detecting AI-generated images (AIGI) remains challenging because detectors often fail to generalize to unseen generators. Although existing methods
arXiv:2605.26362v1 Announce Type: cross Abstract: In many reasoning tasks, large language models (LLMs) rely on structured external knowledge, such as graphs and tables, which is typically linearized
Yes, it was easier to laugh, or cry, at such lunacy in medical and scientific officialdom in banana republics like Russia before Trump appointed RFK Jr (circumcision and vaccines cause autism, mRNA te
arXiv:2502.17666v4 Announce Type: replace-cross Abstract: Existing offline in-context reinforcement learning (ICRL) methods have predominantly relied on supervised training objectives, which are known
arXiv:2605.25640v1 Announce Type: cross Abstract: Accurate reconstruction of magnetic fields in inaccessible regions is vital for many high-precision experiments in physics. Traditional methods, such
arXiv:2505.22322v3 Announce Type: replace Abstract: Diffusion models have shown strong performance in generating high-quality tabular data, but they carry privacy risks by reproducing exact training s
arXiv:2601.00553v2 Announce Type: replace-cross Abstract: Multimodal generative AI systems like Stable Diffusion, DALL-E, and MidJourney have fundamentally changed how synthetic images are created. Th