Search: “research”

Risk-aware Selective Prompting for Hallucination Mitigation in Large Vision-Language Models

arXiv:2605.28123v1 Announce Type: new Abstract: Prompt-based verification is widely used to mitigate hallucinations in large vision-language models (LVLMs), yet when it helps remains poorly understood

Research

Risk-Controlled Lean-as-Judge for Natural-Language Mathematical Reasoning

DGX agent

arXiv:2605.28365v1 Announce Type: new Abstract: Lean is increasingly used to judge natural-language mathematical answers, but its signal is partial: many answers never formalize, and a failed proof ma

researcharxiv-cs-ai

28 May 2026

RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs

arXiv:2509.21128v2 Announce Type: replace Abstract: Large language models (LLMs) are typically trained by reinforcement learning (RL) with verifiable rewards (RLVR) and supervised fine-tuning (SFT) on

RULER: Representation-Level Verification of Machine Unlearning

arXiv:2605.27569v1 Announce Type: new Abstract: Machine unlearning aims to remove the influence of specific training records from a deployed model without retraining from scratch. Current protocols ve

SAFE-Diff: Scale-Aware Attention and Feature-Dispersive Diffusion with Uncertainty Estimation for Contrast-Enhanced Breast MRI Synthesis

arXiv:2605.25767v2 Announce Type: replace Abstract: Synthesizing high fidelity contrast enhanced MRI is clinically valuable for safer and more efficient breast cancer screening, yet remains challengin

SANTS: A State-Adaptive Scheduler for World Action Models

arXiv:2605.27947v1 Announce Type: new Abstract: World Action Models (WAMs) improve robot manipulation by using video-based future representations to condition action generation. In pixel-space WAMs, h

researcharxiv-cs-ro

Satisfiability Solving with LLMs: A Matched-Pair Evaluation of Reasoning Capability

arXiv:2605.28602v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for tasks that implicitly reduce to Boolean satisfiability (SAT), yet their reasoning ability on SAT

Score Based Error Correcting Code Decoder

arXiv:2605.28358v1 Announce Type: cross Abstract: Error-correcting codes enable reliable communication, yet practical soft decoding remains challenging across code families and block lengths. We propo

Self-Consistency via Marginal Sharpening

arXiv:2605.28142v1 Announce Type: cross Abstract: Inference-time sampling can elicit strong reasoning abilities from language models without additional training. Existing power-sampling methods do so

Self-Prophetic Decoding to Unlock Visual Search in LVLMs

arXiv:2605.28741v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) are rapidly evolving toward true multimodal reasoning, with visual search representing a concrete instantiation of

SelfJudge: Faster Speculative Decoding via Self-Supervised Judge Verification

arXiv:2510.02329v2 Announce Type: replace-cross Abstract: Speculative decoding accelerates LLM inference by verifying candidate tokens from a draft model against a larger target model. Recent judge de

Semantic Flow Regularization: Teaching LLMs to Generate Diverse Yet Coherent Responses

arXiv:2605.27971v1 Announce Type: cross Abstract: When large language models are fine-tuned to generate persona- or tone-conditioned responses, their output diversity is severely limited--a failure we

Semantic-level Backdoor Attack against Text-to-Image Diffusion Models

arXiv:2602.04898v3 Announce Type: replace-cross Abstract: Text-to-image (T2I) diffusion models are widely adopted for their strong generative capabilities, yet remain vulnerable to backdoor attacks. E

Semantic Optimal Transport for Sparse Autoencoder Feature Matching and Circuit Compression

arXiv:2605.28567v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have become a central tool for interpreting language models. However, two key SAE analyses that remain difficult to scale a

Semi-Supervised Hypothesis Testing by Betting on Predictions

arXiv:2605.28533v1 Announce Type: new Abstract: We introduce a testing-by-betting framework that leverages predictions on unlabeled data to enhance the power of sequential hypothesis testing. Given li

Sequential Neural Probabilistic Amplitude Shaping: Learning the Channel's Language

arXiv:2605.28143v1 Announce Type: new Abstract: We present the first neural probabilistic amplitude shaping that outperforms existing methods while accounting for all implementation losses, using a bl

Short-Term Gain, Long-Term Fragility: AI Labor Substitution and the Erosion of Sustainable Capability

arXiv:2605.27399v1 Announce Type: cross Abstract: What looks like acceleration can be a quiet transfer of burden from the present to the future. Attempts to replace human labor with AI systems are oft

SilentRetrieval: Hijacking Retrieval-Augmented Generation via Semantically-Preserving Adversarial Data Poisoning

arXiv:2605.28074v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) mitigates LLM hallucinations but introduces a critical vulnerability: corpus integrity. We present SilentRetrieva

Sinc Kolmogorov-Arnold network and its application for solving PDEs with singularities

arXiv:2410.04096v2 Announce Type: replace-cross Abstract: In this paper, we propose to use Sinc interpolation in the context of Kolmogorov-Arnold Networks, neural networks with learnable activation fu

Single-Rollout Hidden-State Dynamics for Training-Free RLVR Data Selection

arXiv:2605.28631v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) can yield large reasoning gains from very few training instances, yet its strong sensitivity to wh

Skillful high-resolution weather forecasting independent of physical models

arXiv:2605.28153v1 Announce Type: cross Abstract: Accurate and timely weather forecasts are critical for high-impact decisions in modern society. Machine-learning-based weather prediction is emerging

Smoothed Score Queries and the Complexity of Sampling

arXiv:2605.27769v1 Announce Type: cross Abstract: We study the query complexity of sampling from high-dimensional Gaussian distributions using gradient information. In the standard oracle model, exact

Model Releases

SONIC-O1: A Real-World Benchmark for Evaluating Multimodal Large Language Models on Audio-Video Understanding

model-releasesarxiv-cs-ai

arXiv:2601.21666v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) are a major focus of recent AI research. However, most prior work focuses on static image understanding, wh

Sparse Scheduled Diffusion Guidance for Inverse Problems

arXiv:2603.07860v2 Announce Type: replace Abstract: Pretrained diffusion models are effective priors for Bayesian inverse problems, but posterior sampling with these priors is often costly because dat

SparseOpt: Addressing Normalization-induced Gradient Skew in Sparse Training

arXiv:2605.27541v1 Announce Type: new Abstract: Dynamic Sparse Training (DST) methods train neural networks by maintaining sparsity while dynamically adapting the network topology. Despite the promise

ST-ColoNet: Spatio-Temporal Colon Segment Recognition via Hybrid Attention and Edge-Guided Feature Learning

arXiv:2605.28119v1 Announce Type: new Abstract: Colo-segment recognition in colonoscopy videos is a key requirement for many downstream tasks, but existing automatic recognition methods only use colon

STAB: Specification-driven Testing for Algorithmic Bottlenecks

arXiv:2605.27981v1 Announce Type: new Abstract: Evaluating the efficiency of algorithmic code requires test cases that expose runtime bottlenecks. Previous methods generate efficiency test cases eithe

Stabilizing distribution-free probabilistic forecasts

arXiv:2605.28531v1 Announce Type: new Abstract: Multi-step-ahead forecasts are often updated as new observations become available, since shorter forecast horizons typically improve forecast quality. H

Stance Detection in Prediction Markets: Addressing Imbalanced Trader Commentary via Counterfactual Augmentation and Market Context

arXiv:2605.28745v1 Announce Type: new Abstract: Prediction markets such as Polymarket aggregate crowd beliefs into real-time probability estimates, and the comments traders post beneath each market co

STFlow: Data-Coupled Flow Matching for Geometric Trajectory Simulation

arXiv:2505.18647v3 Announce Type: replace-cross Abstract: Simulating trajectories of dynamical systems is a fundamental problem in a wide range of fields such as molecular dynamics, biochemistry, and

Stop Rewarding Hallucinated Steps: Faithfulness-Aware Step-Level Reinforcement Learning for Small Reasoning Models

arXiv:2602.05897v2 Announce Type: replace Abstract: As large language models become smaller and more efficient, small reasoning models (SRMs) are crucial for enabling chain-of-thought (CoT) reasoning

Structure over Pixels: Learning Variable-Length Visual Programs

arXiv:2605.27696v1 Announce Type: new Abstract: Discrete visual tokenizers translate images into ordered sequences of codes, providing a natural representation for structural description of scenes. Ye

Super-Resolved Canopy Height Mapping from Sentinel-2 Time Series Using Airborne LiDAR HD Reference Data across Metropolitan France

arXiv:2512.11524v3 Announce Type: replace Abstract: Fine-scale forest monitoring is essential for understanding canopy structure and its dynamics, which are key indicators of carbon stocks, biodiversi

Syllabic-Structure Decoder for Automatic Speech Recognition in Vietnamese

arXiv:2605.27874v1 Announce Type: new Abstract: Most Automatic Speech Recognition (ASR) systems formulate transcription as a prediction problem over orthographic units such as characters, subwords, or

Synthetic Emotions vs. Gamification: Exploring Engagement Strategies for Small Social Robots in Different Age Groups

arXiv:2605.27539v1 Announce Type: new Abstract: Many children experience challenges in emotional regulation and social interaction, which can limit their participation in everyday activities and thera

researcharxiv-cs-ro

Tactile-Proprioceptive Sensor Fusion for Contact Wrench Estimation in Whole-Body Physical Human-Robot Interaction

arXiv:2605.28412v1 Announce Type: cross Abstract: Direct physical guidance is a natural means of teaching and interacting with robots, and robotic skins make a key contribution by enabling sensitive c

TARQ: Tail-Aware Reconstruction Quantization for Rare-Word Robust Automatic Speech Recognition

arXiv:2605.27808v1 Announce Type: new Abstract: Data-aware post-training quantization (PTQ) minimizes a per-token reconstruction loss on a small calibration corpus, implicitly weighting positions by t

Tell Me a Story! Narrative-Driven XAI with Large Language Models

arXiv:2309.17057v3 Announce Type: replace Abstract: In many AI applications today, the predominance of black-box machine learning models, due to their typically higher accuracy, amplifies the need for

Text-Only Data Synthesis for Vision Language Model Training

arXiv:2503.22655v2 Announce Type: replace Abstract: Training vision-language models (VLMs) typically requires large-scale, high-quality image-text pairs, but collecting or synthesizing such data is co

The AI Hype Index: AI gets booed in graduation season

It is one thing to say AI will change the world. It is another to expect the class of 2026 to applaud it. In fact, when former Google CEO Eric Schmidt told University of Arizona graduates that their t

researchmit-tech-review

The Computational Boundary of Inference: Capability Internalization, Training, and the Turing Jump

arXiv:2605.27381v1 Announce Type: cross Abstract: Claims about recursive self-improvement in AI often slide from repeated internal revision to the possibility of qualitatively stronger capability with

The Download: climate tech goes public and the AI Hype Index returns

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. Climate tech companies are going public. What’s next? Solar an

researchmit-tech-review

The Fundamental Limits of Fraud Detection in Card Payment Networks

arXiv:2605.27557v1 Announce Type: new Abstract: Card payment fraud detection is usually framed as a supervised classification problem. Although this approach has generated practical progress, improvem

The Future of Facts: Tracing the Factual Generation-Verification Gap

arXiv:2605.27564v1 Announce Type: cross Abstract: Language models are becoming the default interface to factual knowledge, yet they often verify outputs more reliably than they generate them. This gen

The Shape of Reasoning: Topological Analysis of Reasoning Traces in Large Language Models

arXiv:2510.20665v3 Announce Type: replace Abstract: Evaluating the quality of reasoning traces from large language models remains understudied, labor-intensive, and unreliable: current practice relies

The Well-Tempered Classifier: Some Elementary Properties of Temperature Scaling

arXiv:2602.14862v2 Announce Type: replace-cross Abstract: Temperature scaling is a simple method that allows to control the uncertainty of probabilistic models. It is mostly used in two contexts: impr

Thinking as Compression: Your Reasoning Model is Secretly a Context Compressor

arXiv:2605.28713v1 Announce Type: new Abstract: Context compression aims to shorten long context inputs with minimal information loss for LLM inference acceleration. While existing methods have shown

This week alone: DOJ opens an investigation into the woman Trump raped. The White House is caught steering a $620 million contract to Don Jr…

This week alone: DOJ opens an investigation into the woman Trump raped. The White House is caught steering a 620 million contract to Don Jr.’s firm. The Pentagon hands out a 10 billion contract after

researchyann-lecun--x