Search: “research”

SOAR: Scale Optimization for Accurate Reconstruction in NVFP4 Quantization

arXiv:2605.12245v1 Announce Type: new Abstract: NVFP4 has recently emerged as an efficient 4-bit microscaling format for large language models (LLMs), offering superior numerical fidelity with native

Sobolev Regularized MMD Gradient Flow

DGX agent

arXiv:2605.11884v1 Announce Type: new Abstract: We propose Sobolev-regularized Maximum Mean Discrepancy (SrMMD) gradient flow, a regularized variant of maximum mean discrepancy (MMD) gradient flow bas

researcharxiv-cs-lg

13 May 2026

SoK: Unlearnability and Unlearning for Model Dememorization

arXiv:2605.11592v1 Announce Type: new Abstract: Advanced model dememorization methods, including availability poisoning (unlearnability) and machine unlearning, are emerging as key safeguards against

Sparse Attention Remapping with Clustering for Efficient LLM Decoding on PIM

arXiv:2505.05772v2 Announce Type: replace Abstract: Transformer-based models are the foundation of modern machine learning, but their execution, particularly during autoregressive decoding in large la

SpatialForge: Bootstrapping 3D-Aware Spatial Reasoning from Open-World 2D Images

arXiv:2605.11462v1 Announce Type: new Abstract: Recent advancements in Large Vision-Language Models (VLMs) have demonstrated exceptional semantic understanding, yet these models consistently struggle

Spectral Vision Transformer for Efficient Tokenization with Limited Data

arXiv:2605.12026v1 Announce Type: new Abstract: We propose a novel spectral vision transformer architecture for efficient tokenization in limited data, with an emphasis on medical imaging. We outline

Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation

arXiv:2605.12000v1 Announce Type: new Abstract: This work investigates multi-objective imitation learning: the problem of recovering policies that lie on the Pareto front given demonstrations from mul

SRG: Score-based Relaxation-guided Generation for Mixed Integer Linear Programming

arXiv:2603.24033v2 Announce Type: replace Abstract: We propose Score-based Relaxation-guided Generation (SRG), a generative framework based on an approximate formulation of relaxation-guided stochasti

Stationary MMD Points

arXiv:2505.20754v3 Announce Type: replace-cross Abstract: Approximation of a target probability distribution using a finite set of points is a problem of fundamental importance in numerical integratio

Steerable Neural ODEs on Homogeneous Spaces

arXiv:2605.11133v1 Announce Type: new Abstract: We introduce steerable neural ordinary differential equations on homogeneous spaces M=G/H. These models constitute a novel geometric extension of manifo

Steering Without Breaking: Mechanistically Informed Interventions for Discrete Diffusion Language Models

arXiv:2605.10971v1 Announce Type: cross Abstract: Discrete diffusion language models (DLMs) generate text by iteratively denoising all positions in parallel, offering an alternative to autoregressive

Stop Marginalizing My Dreams: Model Inversion via Laplace Kernel for Continual Learning

arXiv:2605.11804v1 Announce Type: cross Abstract: Data-free continual learning (DFCIL) relies on model inversion to synthesize pseudo-samples and mitigate catastrophic forgetting. However, existing in

Stopping Computation for Converged Tokens in Masked Diffusion-LM Decoding

arXiv:2602.06412v3 Announce Type: replace Abstract: Masked Diffusion Language Models generate sequences via iterative sampling that progressively unmasks tokens. However, they still recompute the atte

Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space

arXiv:2605.12412v1 Announce Type: new Abstract: Large Language Models (LLMs) update their behavior in context, which can be viewed as a form of Bayesian inference. However, the structure of the latent

Streaming of rendered content with adaptive frame rate and resolution

arXiv:2605.10995v1 Announce Type: cross Abstract: Streaming rendered content is an attractive way to bring high-quality graphics to billions of mobile devices that do not have sufficient rendering pow

SurvBench: A Standardised Preprocessing Pipeline for Multi-Modal Electronic Health Record Survival Analysis

arXiv:2511.11935v2 Announce Type: replace Abstract: Deep-learning survival models for electronic health record (EHR) data are hard to compare across papers because the upstream preprocessing step, whi

Tackling Fake Forgetting through Uncertainty Quantification

arXiv:2501.19403v3 Announce Type: replace Abstract: Machine unlearning seeks to remove the influence of specified data from a trained model. While the unlearning accuracy provides a widely used metric

Taking the Road Less Scheduled with Adaptive Polyak Steps

arXiv:2511.07767v2 Announce Type: replace Abstract: Schedule-Free SGD, proposed in [Defazio et al., 2024], achieves optimal convergence rates without requiring the training horizon in advance, by repl

Taming Score-Based Denoisers in ADMM: A Convergent Plug-and-Play Framework

arXiv:2603.10281v3 Announce Type: replace-cross Abstract: While score-based generative models have emerged as powerful priors for solving inverse problems, directly integrating them into optimization

Targeted Tests for LLM Reasoning: An Audit-Constrained Protocol

arXiv:2605.11599v1 Announce Type: new Abstract: Fixed reasoning benchmarks evaluate canonical prompts, but semantically valid changes in presentation can still change model behavior. Studies of prompt

Task-Adaptive Embedding Refinement via Test-time LLM Guidance

arXiv:2605.12487v1 Announce Type: new Abstract: We explore the effectiveness of an LLM-guided query refinement paradigm for extending the usability of embedding models to challenging zero-shot search

TCP-SSM: Efficient Vision State Space Models with Token-Conditioned Poles

arXiv:2605.11563v1 Announce Type: new Abstract: State Space Models (SSMs) have emerged as a compelling alternative to attention models for long-range vision tasks, offering input-dependent recurrence

Testing General Relativity Through Gravitational Wave Classification: A Convolutional Neural Network Framework

arXiv:2605.02453v1 Announce Type: cross Abstract: We present a machine learning framework for testing general relativity (GR) with gravitational wave signals from binary black hole mergers. Using the

The Algorithmic Caricature: Auditing LLM-Generated Political Discourse Across Crisis Events

arXiv:2605.12452v1 Announce Type: new Abstract: Large Language Models (LLMs) can generate fluent political text at scale, raising concerns about synthetic discourse during crises and social conflict.

The Bicameral Model: Bidirectional Hidden-State Coupling Between Parallel Language Models

arXiv:2605.11167v1 Announce Type: new Abstract: Existing multi-model and tool-augmented systems communicate by generating text, serializing every exchange through the output vocabulary. Can two pretra

The Challenge and Reward of Fair Play in Narrative: A Computational Approach

arXiv:2507.13841v2 Announce Type: replace Abstract: Good storytelling involves surprise -- unpredictability in how the story unfolds -- and sense-making, the requirement that the story forms a coheren

The Download: making drugs in orbit and NASA’s nuclear-powered spacecraft

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. A plan to make drugs in orbit is going commercial A startup ca

researchmit-tech-review

The first global agricultural field boundary map at 10m resolution

arXiv:2605.11055v1 Announce Type: new Abstract: The agricultural field is the natural unit at which crops are planted, managed, regulated, and reported, yet most global remote-sensing products for agr

The Midas Touch for Metric Depth

arXiv:2605.11578v1 Announce Type: new Abstract: Recent advances have markedly improved the cross-scene generalization of relative depth estimation, yet its practical applicability remains limited by t

The Offline-Frontier Shift: Diagnosing Distributional Limits in Generative Multi-Objective Optimization

arXiv:2602.11126v2 Announce Type: replace Abstract: Offline multi-objective optimization (MOO) aims to recover Pareto-optimal designs given a finite, static dataset. Recent generative approaches, incl

Think, then Score: Decoupled Reasoning and Scoring for Video Reward Modeling

arXiv:2605.05922v2 Announce Type: replace Abstract: Recent advances in generative video models are increasingly driven by post-training and test-time scaling, both of which critically depend on the qu

Hardware

To Err Is Human; To Annotate, SILICON? Toward Robust Reproducibility in LLM Annotation

arXiv:2412.14461v4 Announce Type: replace Abstract: Unstructured text data annotation is foundational to management research. LLMs offer a cost-effective and scalable alternative to human annotation,

hardwarearxiv-cs-cl

TRACE: Temporal Routing with Autoregressive Cross-channel Experts for EEG Representation Learning

arXiv:2605.11380v1 Announce Type: new Abstract: Learning transferable representations for electroencephalography (EEG) remains challenging because EEG signals are inherently multi-channel and non-stat

Training-Inference Consistent Segmented Execution for Long-Context LLMs

arXiv:2605.11744v1 Announce Type: new Abstract: Transformer-based large language models face severe scalability challenges in long-context generation due to the computational and memory costs of full-

Uniform Scaling Limits in AdamW-Trained Transformers

arXiv:2605.11059v1 Announce Type: cross Abstract: We study the large-depth limit of transformers trained with AdamW, by modelling the hidden-state dynamics as an interacting particle system (IPS) coup

Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data

arXiv:2605.11170v1 Announce Type: new Abstract: Noise-based certified machine unlearning currently faces a hard ceiling: the noise magnitude required to certify unlearning typically destroys model uti

Unlocking Compositional Generalization in Continual Few-Shot Learning

arXiv:2605.11710v1 Announce Type: cross Abstract: Object-centric representations promise a key property for few-shot learning: Rather than treating a scene as a single unit, a model can decompose it i

Unpacking the Eye of the Beholder: Social Location, Identity, and the Moving Target of Political Perspectives

arXiv:2605.11166v1 Announce Type: new Abstract: Political and social identities structure how people evaluate political information, a finding decades deep in political science and routinely discarded

USEMA: a Scalable Efficient Mamba Like Attention for Medical Image Segmentation

arXiv:2605.11131v1 Announce Type: new Abstract: Accurate medical image segmentation is an integral part of the medical image analysis pipeline that requires the ability to merge local and global infor

Variational Linear Attention: Stable Associative Memory for Long-Context Transformers

arXiv:2605.11196v1 Announce Type: new Abstract: Linear attention reduces the quadratic cost of softmax attention to O(T), but its memory state grows as O(T) in Frobenius norm, causing progressive inte

Vector Scaffolding: Inter-Scale Orchestration for Differentiable Image Vectorization

arXiv:2605.11913v1 Announce Type: new Abstract: Differentiable vector graphics have enabled powerful gradient-based optimization of vector primitives directly from raster images. However, existing fra

Vertex-Softmax: Tight Transformer Verification via Exact Softmax Optimization

arXiv:2605.10974v1 Announce Type: new Abstract: Certified verification of transformer attention requires bounding the softmax function over interval constraints on the pre-softmax scores. Existing ver

VidSplat: Gaussian Splatting Reconstruction with Geometry-Guided Video Diffusion Priors

arXiv:2605.11424v1 Announce Type: new Abstract: Gaussian Splatting has achieved remarkable progress in multi-view surface reconstruction, yet it exhibits notable degradation when only few views are av

Vision-aligned Latent Reasoning for Multi-modal Large Language Model

arXiv:2602.04476v2 Announce Type: replace Abstract: Despite recent advancements in Multi-modal Large Language Models (MLLMs) on diverse understanding tasks, these models struggle to solve problems whi

When Brains Disagree: Biological Ambiguity Underlies the Challenge of Amyloid PET Synthesis from Structural MRI

arXiv:2605.11867v1 Announce Type: new Abstract: Structural MRI-to-amyloid PET synthesis has been proposed as a non-invasive alternative for amyloid assessment in Alzheimer's disease (AD). However, rep

When Emotion Becomes Trigger: Emotion-style dynamic Backdoor Attack Parasitising Large Language Models

arXiv:2605.11612v1 Announce Type: new Abstract: Backdoor vulnerabilities widely exist in the fine-tuning of large language models(LLMs). Most backdoor poisoning methods operate mainly at the token lev

When Looking Is Not Enough: Visual Attention Structure Reveals Hallucination in MLLMs

arXiv:2605.11559v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have become a key interface for visual reasoning and grounded question answering, yet they remain vulnerable to

When the Gold Standard Isn't Necessarily Standard: Challenges of Evaluating the Translation of User-Generated Content

arXiv:2512.17738v2 Announce Type: replace Abstract: User-generated content (UGC) is characterised by frequent use of non-standard language, from spelling errors to expressive choices such as slang, ch