research

TAG: Tangential Amplifying Guidance for Hallucination-Resistant Sampling

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

Tail-Aware HiFloat4: W4A4 Post-Training Quantization for Wan2.2

DGX agent

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

researcharxiv-cs-ai

27 May 2026

TailedCore: Few-Shot Sampling for Unsupervised Long-Tail Noisy Anomaly Detection

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

Targeted Remasking: Replacing Token Editing with Token-to-Mask Refinement in Discrete Diffusion Language Models

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

TCBiRRT: Rapid Motion Planning for Tightly Coupled Dual-arm Space Manipulator Using Task-space Random Expansion

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-

Tetris: Tile-level Sampling for Efficient and High-Fidelity Video Object Tracking

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

The Attribution Blind Spot: Detecting When Language Models Rely on Memory Rather Than Retrieved Context

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

The Daily Dose: Workflow-Integrated Large Language Model Automation for Clinical Summarization and Trial Identification in Radiation Oncology

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

The Download: keeping up with AI, and the future of IVF

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

researchmit-tech-review

today was a massive day for protein engineering. esmfold2 dropped—next gen of the esm series, fully open on @huggingscience. 1.1 billion pre…

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

Touch-R1: Reinforcing Touch Reasoning in MLLMs

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.

Tournament-GRPO: Group-Wise Tournament Rewards for Reinforcement Learning in Open-Ended Long-Form Generation

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

Towards Controllable Image Generation through Representation-Conditioned Diffusion Models

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

Towards Drone-based Mapping of Volcanic Gases using Gas Tomography

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

Towards Shared Embodied Intelligence in Humanoid Robots through Optimization Development and Testing of the Human Aware ergoCub Robot

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

Tracing Computation Density in LLMs

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

TrackRef3D: Multi-View Consistent Track-then-Label for Open-World Referring Segmentation in 3D Gaussian Splatting

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

Training-Free Vector Quantization via Gaussian VAEs

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

Transfer Learning using 66 Diseases for Disease Forecasting Applications

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 raisi…

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…

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

TSFMAudit: Data Contamination Auditing in Forecasting Time Series Foundation Models

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

TWIST: Closed-Loop token Synchronization for Application-Aware Wireless Digital Twins

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

Two Speeds of Learning: A Representation-Readout Decomposition of Grokking and Double Descent

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

Uncertainty-Aware Budget Allocation for Adaptive Test-Time Reasoning

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

Understanding the Challenges in Iterative Generative Optimization with LLMs

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

Unified Neural Scaling Laws

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

Unified Panoramic Geometry Estimation via Multi-View Foundation Models

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

Unsupervised Deep Image Prior for Sparse-View and Limited-Angle Electron Tomography

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

UPOCR: Towards Unified Pixel-Level OCR Interface

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,

Vector Fields for Path Following on Lie Groups with Application in Robot Control

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

Verilog-Evolve: Feedback-Driven and Skill-Evolving Verilog Generation

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

When Correct Demonstrations Hurt: Rethinking the Role of Exemplars in In-Context Learning

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

When Does Demographic Information Help? Data and Modeling Regimes for Perspective-Aware Hate Speech Detection

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

When Muon Optimizer Meets Adversarial Training: A Theoretical and Empirical Study

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

When Rule Violations Are Rare: Chimera Training for Logical Anomaly Detection

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

Where Detectors Fail: Probing Generative Space for Generalizable AI-Generated Image Detection

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

Why LLMs Hallucinate on Structured Knowledge: A Mechanistic Analysis of Reasoning over Linearized Representations

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 appoi…

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

Yes, Q-learning Helps Offline In-Context RL

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

3D Magnetic Field Reconstruction and Mapping with Physics-Informed Neural Networks

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

A Closer Look on Memorization in Tabular Diffusion Model: A Data-Centric Perspective

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

A Comprehensive Dataset for Human vs. AI Generated Image Detection

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

A Deep Dive into Axiomatic Design -- Part I: Problem Formulation

arXiv:2605.25735v1 Announce Type: new Abstract: Problem formulation translating customer needs and constraints into a minimum set of independent first-level functional requirements, is arguably the mo

A Dynamical Framework for Cognitive Processes Based on Transformations and Semantic Equivalence

arXiv:2605.23942v1 Announce Type: new Abstract: This paper proposes a structural and dynamical framework for modeling cognitive processes within a cybernetic perspective. Cognitive states are represen

A general tensor-structured compression scheme for efficient large language models

arXiv:2605.25344v1 Announce Type: cross Abstract: Large language models (LLMs) are dominated by dense linear transformations, whose storage, memory and computational overheads hinder efficient adaptat

A Generative Approach for Semantic Auditing of Electronic Health Records

arXiv:2507.02628v2 Announce Type: replace Abstract: The reliability of clinical artificial intelligence (AI) depends on high-quality data, yet Electronic Health Records are often inconsistent with exi

A Greedy Hierarchical Approach to Whole-Network Filter-Pruning in CNNs

arXiv:2409.03777v3 Announce Type: replace-cross Abstract: Deep convolutional neural networks (CNNs) have achieved impressive performance in many computer vision tasks. However, their large model sizes