research

StageMem: Lifecycle-Managed Memory for Language Models

arXiv:2604.16774v1 Announce Type: new Abstract: Long-horizon language model systems increasingly rely on persistent memory, yet many current designs still treat memory primarily as a static store: wri

STEP-PD: Stage-Aware and Explainable Parkinson's Disease Severity Classification Using Multimodal Clinical Assessments

DGX agent

arXiv:2604.17611v1 Announce Type: new Abstract: Parkinson's disease (PD) is a progressive disorder in which symptom burden and functional impairment evolve over time, making severity staging essential

researcharxiv-cs-lg

21 Apr 2026

Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMs

arXiv:2602.11528v2 Announce Type: replace-cross Abstract: Recent studies have shown that large language models (LLMs) can infer private user attributes (e.g., age, location, gender) from user-generate

StrEBM: A Structured Latent Energy-Based Model for Blind Source Separation

arXiv:2604.17381v1 Announce Type: cross Abstract: This paper proposes StrEBM, a structured latent energy-based model for source-wise structured representation learning. The framework is motivated by a

String Seed of Thought: Prompting LLMs for Distribution-Faithful and Diverse Generation https://arxiv.org/abs/2510.21150 https://pub.sakana.…

This paper presents a prompting technique called 'String Seed of Thought' that enables large language models to generate outputs that are both faithful to underlying data distributions and maintain di

researchdavid-ha--x

Structured 3D-SVD: A Practical Framework for the Compression and Reconstruction of Biological Volumetric Images

arXiv:2604.16947v1 Announce Type: cross Abstract: This work introduces Structured 3D-SVD as a practical framework for the reconstruction, compression, and analysis of biological volumetric data. Inspi

Style-Based Neural Architectures for Real-Time Weather Classification

arXiv:2604.18251v1 Announce Type: new Abstract: In this paper, we present three neural network architectures designed for real-time classification of weather conditions (sunny, rain, snow, fog) from i

Style over Story: Measuring LLM Narrative Preferences via Structured Selection

arXiv:2510.02025v4 Announce Type: replace Abstract: We introduce a constraint-selection-based experiment design for measuring narrative preferences of Large Language Models (LLMs). This design offers

SVL: Goal-Conditioned Reinforcement Learning as Survival Learning

arXiv:2604.17551v1 Announce Type: new Abstract: Standard approaches to goal-conditioned reinforcement learning (GCRL) that rely on temporal-difference learning can be unstable and sample-inefficient d

SYMBOLIZER: Symbolic Model-free Task Planning with VLMs

arXiv:2604.17830v1 Announce Type: new Abstract: Traditional Task and Motion Planning (TAMP) systems depend on physics models for motion planning and discrete symbolic models for task planning. Althoug

researcharxiv-cs-ro

Symmetry Guarantees Statistic Recovery in Variational Inference

arXiv:2604.18310v1 Announce Type: cross Abstract: Variational inference (VI) is a central tool in modern machine learning, used to approximate an intractable target density by optimising over a tracta

Synthetic Data Generation for Training Diversified Commonsense Reasoning Models

arXiv:2603.18361v2 Announce Type: replace Abstract: Conversational agents are required to respond to their users not only with high quality (i.e. commonsense bearing) responses, but also considering m

Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluation

arXiv:2510.09671v2 Announce Type: replace Abstract: Table Question Answering (TQA) aims to answer natural language questions about tabular data, often accompanied by additional contexts such as text p

Tailoring Diagnostic Modeling to Individual Learners: Personalized Distractor Generation via MCTS-Guided Reasoning Reconstruction

arXiv:2508.11184v2 Announce Type: replace Abstract: Distractors-incorrect yet plausible answer choices in multiple-choice questions (MCQs)-are vital in educational assessments, as they help identify s

Target Parameterization in Diffusion Models for Nonlinear Spatiotemporal System Identification

arXiv:2604.17566v1 Announce Type: cross Abstract: Machine learning is becoming increasingly important for nonlinear system identification, including dynamical systems with spatially distributed output

Test-Time Perturbation Learning with Delayed Feedback for Vision-Language-Action Models

arXiv:2604.18107v1 Announce Type: new Abstract: Vision-Language-Action models (VLAs) achieve remarkable performance in sequential decision-making but remain fragile to subtle environmental shifts, suc

Test-Time Reasoners Are Strategic Multiple-Choice Test-Takers

arXiv:2510.07761v2 Announce Type: replace Abstract: Large language models (LLMs) now give reasoning before answering, excelling in tasks like multiple-choice question answering (MCQA). Yet, a concern

TextTIGER: Text-based Intelligent Generation with Entity Prompt Refinement for Text-to-Image Generation

arXiv:2504.18269v2 Announce Type: replace Abstract: When generating images from prompts that include specific entities, the model must retain as much entity-specific knowledge as possible. However, th

TGLF-WINN: Data-Efficient Deep Learning Surrogate for Turbulent Transport Modeling in Fusion

arXiv:2509.07024v2 Announce Type: replace-cross Abstract: The Trapped Gyro-Landau Fluid (TGLF) model provides fast, accurate predictions of turbulent transport in tokamaks, but whole device simulation

The Collaboration Gap in Human-AI Work

arXiv:2604.18096v1 Announce Type: cross Abstract: LLMs are increasingly presented as collaborators in programming, design, writing, and analysis. Yet the practical experience of working with them ofte

The Gait Signature of Frailty: Transfer Learning based Deep Gait Models for Scalable Frailty Assessment

arXiv:2603.24434v2 Announce Type: replace Abstract: Frailty is a condition in aging medicine characterized by diminished physiological reserve and increased vulnerability to stressors. However, frailt

The GDN-CC Dataset: Automatic Corpus Clarification for AI-enhanced Democratic Citizen Consultations

arXiv:2601.14944v3 Announce Type: replace Abstract: LLMs are ubiquitous in modern NLP, and while their applicability extends to texts produced for democratic activities such as online deliberations or

The impact of postediting on AI generative translation in Yemeni context: Translating literary prose by ChatGPT

arXiv:2604.16704v1 Announce Type: new Abstract: This study examines the role of artificial intelligence in translation, focusing on ChatGPT, specifically ChatGPT-4, and the extent to which human poste

The new word in home construction could be “plastics”

Single-use plastics are a persistent source of environmental pollution, and the need to house a growing global population puts increasing pressure on resources such as timber. MIT engineers have an id

researchmit-tech-review

The Potential of Second-Order Optimization for LLMs: A Study with Full Gauss-Newton

arXiv:2510.09378v2 Announce Type: replace Abstract: Recent efforts to accelerate LLM pretraining have focused on computationally-efficient approximations that exploit second-order structure. This rais

The Topological Trouble With Transformers

arXiv:2604.17121v1 Announce Type: new Abstract: Transformers encode structure in sequences via an expanding contextual history. However, their purely feedforward architecture fundamentally limits dyna

ThinkBrake: Efficient Reasoning via Log-Probability Margin Guided Decoding

arXiv:2510.00546v5 Announce Type: replace Abstract: Large Reasoning Models (LRMs) allocate substantial inference-time compute to Chain-of-Thought (CoT) reasoning, improving performance on mathematics,

This tool could show how consciousness works

How does the physical matter in our brains translate into thoughts, sensations, and emotions? It’s hard to explore that question without neurosurgery. But in a recent paper, MIT philosopher Matthias M

researchmit-tech-review

ThreadSumm: Summarization of Nested Discourse Threads Using Tree of Thoughts

arXiv:2604.17648v1 Announce Type: new Abstract: Summarizing deeply nested discussion threads requires handling interleaved replies, quotes, and overlapping topics, which standard LLM summarizers strug

Tight Auditing of Differential Privacy in MST and AIM

arXiv:2604.18352v1 Announce Type: cross Abstract: State-of-the-art Differentially Private (DP) synthetic data generators such as MST and AIM are widely used, yet tightly auditing their privacy guarant

Tight Clusters Make Specialized Experts

arXiv:2502.15315v3 Announce Type: replace Abstract: Sparse Mixture-of-Experts (MoE) architectures have emerged as a promising approach to decoupling model capacity from computational cost. At the core

Tighter Performance Theory of FedExProx

arXiv:2410.15368v2 Announce Type: replace-cross Abstract: We revisit FedExProx - a recently proposed distributed optimization method designed to enhance convergence properties of parallel proximal alg

Time-Division Multiplexing Actuation in Tendon-Driven Arms: Lightweight Design and Fault Tolerance

arXiv:2604.16887v1 Announce Type: new Abstract: Robotic manipulators for aerospace applications require a delicate balance between lightweight construction and fault-tolerant operation to satisfy stri

researcharxiv-cs-ro

TMD-TTS: A Unified Tibetan Multi-Dialect Text-to-Speech Framework for U-Tsang, Amdo and Kham Speech Dataset Generation

arXiv:2509.18060v2 Announce Type: replace Abstract: Tibetan is a low-resource language with limited parallel speech corpora spanning its three major dialects (U-Tsang, Amdo, and Kham), limiting progre

ToLL: Topological Layout Learning with Asymmetric Cross-View Structural Distillation for 3D Scene Graph Generation Pretraining

arXiv:2603.28178v2 Announce Type: replace Abstract: 3D Scene Graph (3DSG) generation plays a pivotal role in spatial understanding and affordance perception. To mitigate generalization issues from dat

ToMMeR -- Efficient Entity Mention Detection from Large Language Models

arXiv:2510.19410v2 Announce Type: replace Abstract: Identifying which text spans refer to entities - mention detection - is both foundational for information extraction and a known performance bottlen

Tool Learning Needs Nothing More Than a Free 8B Language Model

arXiv:2604.17739v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a prevalent paradigm for training tool calling agents, which typically requires online interactive environments

Topology Structure Optimization of Reservoirs Using GLMY Homology

arXiv:2509.11612v3 Announce Type: replace Abstract: Reservoir is an efficient network for time series processing. It is well known that network structure is one of the determinants of its performance.

Toward Efficient Influence Function: Dropout as a Compression Tool

arXiv:2509.15651v2 Announce Type: replace Abstract: Assessing the impact the training data on machine learning models is crucial for understanding the behavior of the model, enhancing the transparency

Towards Deep Encrypted Training: Low-Latency, Memory-Efficient, and High-Throughput Inference for Privacy-Preserving Neural Networks

arXiv:2604.16834v1 Announce Type: cross Abstract: Privacy-preserving machine learning (PPML) has become increasingly important in applications where sensitive data must remain confidential. Homomorphi

Towards Disentangled Preference Optimization Dynamics Beyond Likelihood Displacement

arXiv:2604.18239v1 Announce Type: new Abstract: Preference optimization is widely used to align large language models (LLMs) with human preferences. However, many margin-based objectives suppress the

Towards E-Value Based Stopping Rules for Bayesian Deep Ensembles

arXiv:2604.18089v1 Announce Type: new Abstract: Bayesian Deep Ensembles (BDEs) represent a powerful approach for uncertainty quantification in deep learning, combining the robustness of Deep Ensembles

Towards Initialization-dependent and Non-vacuous Generalization Bounds for Overparameterized Shallow Neural Networks

arXiv:2604.00505v2 Announce Type: replace Abstract: Overparameterized neural networks often show a benign overfitting property in the sense of achieving excellent generalization behavior despite the n

Towards Real-Time ECG and EMG Modeling on mu NPUs

arXiv:2604.18067v1 Announce Type: new Abstract: The miniaturisation of neural processing units (NPUs) and other low-power accelerators has enabled their integration into microcontroller-scale wearable

Towards Reliable Testing of Machine Unlearning

arXiv:2604.16536v1 Announce Type: new Abstract: Machine learning components are now central to AI-infused software systems, from recommendations and code assistants to clinical decision support. As re

Towards Symmetry-sensitive Pose Estimation: A Rotation Representation for Symmetric Object Classes

arXiv:2604.18208v1 Announce Type: new Abstract: Symmetric objects are common in daily life and industry, yet their inherent orientation ambiguities that impede the training of deep learning networks f

Trajectory-Restricted Optimization Conditions and Geometry-Aware Linear Convergence

arXiv:2604.17067v1 Announce Type: cross Abstract: Linear convergence of first-order methods is typically characterized by global optimization conditions whose constants reflect worst-case geometry of

TSegAgent: Zero-Shot Tooth Segmentation via Geometry-Aware Vision-Language Agents

arXiv:2603.19684v2 Announce Type: replace Abstract: Automatic tooth segmentation and identification from intra-oral scanned 3D models are fundamental problems in digital dentistry, yet most existing a