research

Self-Correcting RAG: Enhancing Faithfulness via MMKP Context Selection and NLI-Guided MCTS

arXiv:2604.10734v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) substantially extends the knowledge boundary of large language models. However, it still faces two major challenges

Research

Semantic-Space Exploration and Exploitation in RLVR for LLM Reasoning

DGX agent

arXiv:2509.23808v4 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) for LLM reasoning is often framed as balancing exploration and exploitation in action sp

researcharxiv-cs-cl

14 Apr 2026

SemEnrich: Self-Supervised Semantic Enrichment of Radiology Reports for Vision-Language Learning

arXiv:2604.09887v1 Announce Type: new Abstract: Medical vision-language datasets are often limited in size and biased toward negative findings, as clinicians report abnormalities mostly but might omit

SEPTQ: A Simple and Effective Post-Training Quantization Paradigm for Large Language Models

arXiv:2604.10091v1 Announce Type: new Abstract: Large language models (LLMs) have shown remarkable performance in various domains, but they are constrained by massive computational and storage costs.

Seven simple steps for log analysis in AI systems

arXiv:2604.09563v1 Announce Type: new Abstract: AI systems produce large volumes of logs as they interact with tools and users. Analysing these logs can help understand model capabilities, propensitie

ShapShift: Explaining Model Prediction Shifts with Subgroup Conditional Shapley Values

arXiv:2604.11200v1 Announce Type: cross Abstract: Changes in input distribution can induce shifts in the average predictions of machine learning models. Such prediction shifts may impact downstream bu

Sharpness-Aware Surrogate Training for On-Sensor Spiking Neural Networks

arXiv:2604.09696v1 Announce Type: cross Abstract: Spiking neural networks (SNNs) are a natural computational model for on-sensor and near-sensor vision, where event driven processors must operate unde

Should be fixed now, appreciate everyone’s patience!

Nous Research posted a brief status update on X (formerly Twitter) indicating that a previously reported issue has been resolved, thanking their community for their patience during the downtime or dis

researchnous-research--x

Should We be Pedantic About Reasoning Errors in Machine Translation?

arXiv:2604.09890v1 Announce Type: cross Abstract: Across multiple language pairings (English o {Spanish, French, German, Mandarin, Japanese, Urdu, Cantonese}), we find reasoning errors in translation.

SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation

arXiv:2305.09958v5 Announce Type: replace Abstract: Graph neural networks (GNNs) realize great success in graph learning but suffer from performance loss when meeting heterophily, i.e. neighboring nod

Signal-Aware Conditional Diffusion Surrogates for Transonic Wing Pressure Prediction

arXiv:2604.11263v1 Announce Type: cross Abstract: Accurate and efficient surrogate models for aerodynamic surface pressure fields are essential for accelerating aircraft design and analysis, yet deter

Simply retrieving a reasoning trace looks a lot like human reasoning, until it's time to navigate uncharted territory. If you memorized all …

researchfrancois-chollet--x

Simply retrieving a reasoning trace looks a lot like human reasoning, until it's time to navigate uncharted territory. If you memorized all reasoning traces of humans from 10,000 BC, you could automat

SinkTrack: Attention Sink based Context Anchoring for Large Language Models

arXiv:2604.10027v1 Announce Type: new Abstract: Large language models (LLMs) suffer from hallucination and context forgetting. Prior studies suggest that attention drift is a primary cause of these pr

Slithering Through Gaps: Capturing Discrete Isolated Modes via Logistic Bridging

arXiv:2604.10821v1 Announce Type: new Abstract: High-dimensional and complex discrete distributions often exhibit multimodal behavior due to inherent discontinuities, posing significant challenges for

Soft Graph Transformer for MIMO Detection

arXiv:2509.12694v5 Announce Type: replace Abstract: We propose the Soft Graph Transformer (SGT), a soft-input-soft-output neural architecture designed for MIMO detection. While Maximum Likelihood (ML)

Solver-Independent Automated Problem Formulation via LLMs for High-Cost Simulation-Driven Design

arXiv:2512.18682v2 Announce Type: replace Abstract: In the high-cost simulation-driven design domain, translating ambiguous design requirements into a mathematical optimization formulation is a bottle

Solving and learning advective multiscale Darcian dynamics with the Neural Basis Method

arXiv:2602.17776v2 Announce Type: replace-cross Abstract: Physics-governed models are increasingly paired with machine learning for accelerated predictions, yet most 'physics--informed' formulations t

Sparse Hypergraph-Enhanced Frame-Event Object Detection with Fine-Grained MoE

arXiv:2604.11140v1 Announce Type: new Abstract: Integrating frame-based RGB cameras with event streams offers a promising solution for robust object detection under challenging dynamic conditions. How

Spectral Kernel Dynamics via Maximum Caliber: Fixed Points, Geodesics, and Phase Transitions

arXiv:2604.09745v1 Announce Type: cross Abstract: We derive a closed-form geometric functional for kernel dynamics on finite graphs by applying the Maximum Caliber (MaxCal) variational principle to th

SpectralLoRA: Is Low-Frequency Structure Sufficient for LoRA Adaptation? A Spectral Analysis of Weight Updates

arXiv:2604.10649v1 Announce Type: cross Abstract: We present a systematic empirical study of the spectral structure of LoRA weight updates. Through 2D Discrete Cosine Transform (DCT) analysis of train

SpeechLess: Micro-utterance with Personalized Spatial Memory-aware Assistant in Everyday Augmented Reality

arXiv:2602.00793v2 Announce Type: replace-cross Abstract: Speaking aloud to a wearable AR assistant in public can be socially awkward, and re-articulating the same requests every day creates unnecessa

Stability of a Generalized Debiased Lasso with Applications to Resampling-Based Variable Selection

arXiv:2405.03063v2 Announce Type: replace-cross Abstract: We propose a generalized debiased Lasso estimator based on a stability principle. When a single column of the design matrix is perturbed, the

StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs

arXiv:2509.22220v2 Announce Type: replace Abstract: Prevalent semantic speech tokenizers, designed to capture linguistic content, are surprisingly fragile. We find they are not robust to meaning-irrel

STGV: Spatio-Temporal Hash Encoding for Gaussian-based Video Representation

arXiv:2604.10910v1 Announce Type: new Abstract: 2D Gaussian Splatting (2DGS) has recently become a promising paradigm for high-quality video representation. However, existing methods employ content-ag

StreetDesignAI: A Multi-Persona Evaluation System for Inclusive Infrastructure Design

arXiv:2601.15671v2 Announce Type: replace-cross Abstract: Designing cycling infrastructure requires balancing the competing needs of diverse user groups, yet designers often struggle to anticipate how

STS-Mixer: Spatio-Temporal-Spectral Mixer for 4D Point Cloud Video Understanding

arXiv:2604.11637v1 Announce Type: new Abstract: 4D point cloud videos capture rich spatial and temporal dynamics of scenes which possess unique values in various 4D understanding tasks. However, most

STU-PID: Steering Token Usage via PID Controller for Efficient Large Language Model Reasoning

arXiv:2506.18831v2 Announce Type: replace Abstract: Large Language Models employing extended chain-of-thought (CoT) reasoning often suffer from the overthinking phenomenon, generating excessive and re

Subargument Argumentation Frameworks: Separating Direct Conflict from Structural Dependency

arXiv:2601.12038v3 Announce Type: replace Abstract: Dung's abstract argumentation frameworks model acceptability solely in terms of an attack relation, thereby conflating two conceptually distinct asp

Suiren-1.0 Technical Report: A Family of Molecular Foundation Models

arXiv:2603.21942v2 Announce Type: replace-cross Abstract: We introduce Suiren-1.0, a family of molecular foundation models for the accurate modeling of diverse organic systems. Suiren-1.0 comprising t

SwinTextUNet: Integrating CLIP-Based Text Guidance into Swin Transformer U-Nets for Medical Image Segmentation

arXiv:2604.10000v1 Announce Type: new Abstract: Precise medical image segmentation is fundamental for enabling computer aided diagnosis and effective treatment planning. Traditional models that rely s

SyncFix: Fixing 3D Reconstructions via Multi-View Synchronization

arXiv:2604.11797v1 Announce Type: new Abstract: We present SyncFix, a framework that enforces cross-view consistency during the diffusion-based refinement of reconstructed scenes. SyncFix formulates r

SynthAgent: Adapting Web Agents with Synthetic Supervision

arXiv:2511.06101v3 Announce Type: replace-cross Abstract: Web agents struggle to adapt to new websites due to the scarcity of environment specific tasks and demonstrations. Recent works have explored

Tackling multiphysics problems via finite element-guided physics-informed operator learning

arXiv:2603.01420v2 Announce Type: replace Abstract: This work presents a finite element-guied physics-informed learning framework for multiphysics problems with coupled partial differential equations

TaleDiffusion: Multi-Character Story Generation with Dialogue Rendering

arXiv:2509.04123v2 Announce Type: replace Abstract: Text-to-story visualization is challenging due to the need for consistent interaction among multiple characters across frames. Existing methods stru

TAMISeg: Text-Aligned Multi-scale Medical Image Segmentation with Semantic Encoder Distillation

arXiv:2604.10912v1 Announce Type: new Abstract: Medical image segmentation remains challenging due to limited fine-grained annotations, complex anatomical structures, and image degradation from noise,

TAPNext++: What's Next for Tracking Any Point (TAP)?

arXiv:2604.10582v1 Announce Type: new Abstract: Tracking-Any-Point (TAP) models aim to track any point through a video which is a crucial task in AR/XR and robotics applications. The recently introduc

TARAC: Mitigating Hallucination in LVLMs via Temporal Attention Real-time Accumulative Connection

arXiv:2504.04099v2 Announce Type: replace-cross Abstract: Large Vision-Language Models have demonstrated remarkable capabilities, yet they suffer from hallucinations that limit practical deployment. W

Teaching Robots to Interpret Social Interactions through Lexically-guided Dynamic Graph Learning

arXiv:2604.10895v1 Announce Type: cross Abstract: For a robot to be called socially intelligent, it must be able to infer users internal states from their current behaviour, predict the users future b

researcharxiv-cs-ro

Temporal-Aware Spiking Transformer Hashing Based on 3D-DWT

arXiv:2501.06786v2 Announce Type: replace Abstract: With the rapid growth of dynamic vision sensor (DVS) data, constructing a low-energy, efficient data retrieval system has become an urgent task. Has

TerraSky3D: Multi-View Reconstructions of European Landmarks in 4K

arXiv:2603.28287v2 Announce Type: replace Abstract: Despite the growing need for data of more and more sophisticated 3D reconstruction pipelines, we can still observe a scarcity of suitable public dat

Test-time Scaling over Perception: Resolving the Grounding Paradox in Thinking with Images

arXiv:2604.11025v1 Announce Type: new Abstract: Recent multimodal large language models (MLLMs) have begun to support Thinking with Images by invoking visual tools such as zooming and cropping during

The Diffusion-Attention Connection

arXiv:2604.09560v1 Announce Type: new Abstract: Transformers, diffusion-maps, and magnetic Laplacians are usually treated as separate tools; we show they are all different regimes of a single Markov g

The Download: the state of AI, and protecting bears with drones

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. Want to understand the current state of AI? Check out these ch

researchmit-tech-review

The Geometry of Knowing: From Possibilistic Ignorance to Probabilistic Certainty -- A Measure-Theoretic Framework for Epistemic Convergence

arXiv:2604.09614v1 Announce Type: new Abstract: This paper develops a measure-theoretic framework establishing when and how a possibilistic representation of incomplete knowledge contracts into a prob

The greatest triumph of the incessant hurricane of lies coming from Russia, MAGA, and the likes of Elon Musk has been convincing a significa…

The greatest triumph of the incessant hurricane of lies coming from Russia, MAGA, and the likes of Elon Musk has been convincing a significant share of the world, including Europeans, to believe in a

researchyann-lecun--x

The Myth of Expert Specialization in MoEs: Why Routing Reflects Geometry, Not Necessarily Domain Expertise

arXiv:2604.09780v1 Announce Type: new Abstract: Mixture of Experts (MoEs) are now ubiquitous in large language models, yet the mechanisms behind their 'expert specialization' remain poorly understood.

The Phantom of PCIe: Constraining Generative Artificial Intelligences for Practical Peripherals Trace Synthesizing

arXiv:2411.06376v3 Announce Type: replace-cross Abstract: Peripheral Component Interconnect Express (PCIe) is the de facto interconnect standard for high-speed peripherals and CPUs. The development of

The problem with thinking you’re part Neanderthal

You’ve probably heard some version of this idea before: that many of us have an “inner Neanderthal.” That is to say, around 45,000 years ago, when Homo sapiens first arrived in Europe, they met member

researchmit-tech-review