Search: “research”

QUBO-Optimized Evidence Selection for Retrieval-Augmented Question Answering with Unconventional Solvers

arXiv:2607.12334v1 Announce Type: new Abstract: Retrieval-augmented question answering depends on selecting evidence passages that jointly support answer generation. However, many RAG pipelines rely o

Research

Reducing information dependency does not cause training data privacy. Adversarially non-robust features do

DGX agent

arXiv:2607.12354v1 Announce Type: new Abstract: In this paper, we challenge the prevailing view that information dependency (including rote memorization) drives training data exposure to image reconst

researcharxiv-cs-lg

15 Jul 2026

Representation and Reference Selection in Training-Free Synthetic Image Attribution

arXiv:2607.12052v1 Announce Type: cross Abstract: Synthetic image attribution aims at identifying the generator responsible for a given AI-generated image. Training-free reference-based attribution me

Representing and Generating Levels Over Time through Playtrace Reconstructive Partitioning

arXiv:2607.12097v1 Announce Type: new Abstract: Video games are a dynamic medium experienced over time. While there are many Procedural Content Generation (PCG) approaches for generating video game le

RFMSR: Residual Flow Matching for Image Super-Resolution

arXiv:2607.12753v1 Announce Type: new Abstract: Image super-resolution (ISR) has witnessed remarkable progress with diffusion models and flow matching. The dominant text-to-image (T2I) based approache

Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning

arXiv:2607.12395v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards without human-annotated data, often referred to as zero RL, has emerged as a powerful paradigm for elicit

Robust Design of Integrated Sensing and Communication in LEO Satellite Systems

arXiv:2607.12337v1 Announce Type: cross Abstract: With the growing demand for satellite sensing and communication, the limited wireless resources are difficult to support multiple satellite systems. T

Robust In-Hand Manipulation via Priors in Reinforcement Learning and Mechanical Design

arXiv:2607.12105v1 Announce Type: cross Abstract: In-hand manipulation without external sensing is challenging due to uncertainties from finger-object contacts and disturbances by gravity. While reinf

Robustness of Deep Learning Models for PV Power Forecasting under NWP Forecast Errors: A Spatiotemporal and Physically Interpretable Analysis

arXiv:2607.12954v1 Announce Type: cross Abstract: Engineering use of AI forecasting models requires not only high nominal accuracy but also predictable behavior under uncertain inputs. In photovoltaic

Rough Path Signature-Guided Geometry Augmentation for Few-Shot Industrial Surface Defect Detection

arXiv:2607.12245v1 Announce Type: new Abstract: Few-shot industrial defect detection remains difficult for standard supervised detectors, which achieve poor performance on boundary-dominated industria

Same Compression Principle, Different Geometry: Rate-Distortion Signatures Dissociate Biological and Artificial Visual Systems

arXiv:2603.01568v2 Announce Type: replace-cross Abstract: Efficient coding theory predicts that biological perceptual systems compress sensory input optimally under resource constraints, with the syst

Same Loss, Same Noise, Opposite Schedules: Noise Structure and Optimizer Normalization Jointly Determine Whether Learning-Rate Cooldown Helps

arXiv:2607.12360v1 Announce Type: new Abstract: The cooldown phase of a warmup-stable-decay (WSD) learning-rate schedule, now a default in large-model pretraining, lowers the final training loss in so

Saturation Makes Quantization Error Additive: A Coverage Model with a Certificate

arXiv:2607.12266v1 Announce Type: new Abstract: Mixed-precision quantization must decide which parts of a model to keep at higher precision. A common premise, shared by sensitivity-based methods such

Segregate, Refine, Integrate: Decomposing Multimodal Fusion for Sentiment Analysis

arXiv:2607.12686v1 Announce Type: new Abstract: Multimodal fusion must simultaneously refine modality-specific signals and model cross-modal interactions; two competing objectives typically entangled

Semantic-Edge Response Decoding of SAM3 for Zero-Shot Crack Segmentation

arXiv:2607.12292v1 Announce Type: new Abstract: Crack segmentation is essential for infrastructure inspection and structural health assessment, but existing high-performance methods typically require

Semidirect Fourier Delta Attention: Phase-Controlled Delta Memory with Constructive Chunk-WY Kernels

arXiv:2607.11897v1 Announce Type: new Abstract: Linear attention replaces softmax attention's growing KV cache with a fixed recurrent state, but this compression limits exact state tracking and long-c

SinAE: A Single-Architecture Flow-Matching Autoencoder for Cross-Domain Atomic Systems

arXiv:2607.12380v1 Announce Type: new Abstract: Small molecules, crystals, and proteins all reduce to atoms in 3D space, yet their generative pipelines remain fragmented across domains, each with its

SlimPer: Make Personalization Model Slim and Smart

arXiv:2607.12281v1 Announce Type: cross Abstract: Transformer-style architectures are increasingly adopted for industrial recommendation systems, yet they inherit a design premise misaligned with the

Solution of the Hempel's statistical ambiguity problem and Causal AI

arXiv:2607.12826v1 Announce Type: new Abstract: This paper addresses Carl Hempel's longstanding problem of statistical ambiguity in inductive-statistical inference, in which contradictory predictions

Some Complexity Results for Robustness Verification for Binarized Neural Networks

arXiv:2606.18918v2 Announce Type: replace Abstract: This paper studies the computational complexity of verification problems for Binarized Neural Networks (BNNs), where activations (and sometimes weig

Sparse Inter-Layer Dependencies of Transformer FFN Neurons

arXiv:2607.11990v1 Announce Type: cross Abstract: Feedforward network (FFN) blocks account for a large fraction of the parameters and computation in Transformer architectures, yet their internal struc

Spectral Diffusion Processes

arXiv:2209.14125v3 Announce Type: replace-cross Abstract: Diffusion models have proven to be a flexible and effective framework for modelling probability distributions on finite-dimensional spaces. Ho

SpikeDS: Dual Sparsity Spikformer for Perineural Invasion Prediction in 3D MRI

arXiv:2607.11986v1 Announce Type: new Abstract: Perineural invasion (PNI) is associated with poor prognosis in cholangiocarcinoma (CCA). However, its detection from 3D MRI remains challenging due to t

Statistical Non-linear Reconstruction Loss for Image Anomaly Detection

arXiv:2607.12866v1 Announce Type: new Abstract: Reconstruction-based methods are a cornerstone of unsupervised image anomaly detection, but they remain vulnerable to outlier leakage, where standard me

Steering Diffusion Models via Class-Contrastive Influence for Few-Shot Medical Classification

arXiv:2607.12464v1 Announce Type: new Abstract: When labeled data are scarce, off-the-shelf diffusion models can augment training sets for few-shot medical image classification, but not all generated

TAKE: Trajectory-Aware Knowledge Estimation for Text Dataset Distillation

arXiv:2607.11898v1 Announce Type: new Abstract: Large-scale text corpora have become a quiet bottleneck in modern NLP, not just in storage, but in the accumulated cost of training, fine-tuning, and co

The Computational Basis of Confidence in Large Language Models

arXiv:2607.12447v1 Announce Type: cross Abstract: Reliable confidence -- the probability that a model's own answer is correct -- is essential for the trustworthy deployment of language models. Existin

The Geometry of Memorization: Finite-Time Spectral Sensitivity as a Diagnostic for Flow Matching Models

arXiv:2607.12616v1 Announce Type: new Abstract: Continuous-time generative frameworks construct probability paths between base and target domains by optimizing time-dependent velocity fields. While th

The Limits and Potentials of Local SGD for Distributed Heterogeneous Learning with Intermittent Communication

arXiv:2405.11667v2 Announce Type: replace Abstract: Local SGD is a popular optimization method in distributed learning, often outperforming other algorithms in practice, including mini-batch SGD. Desp

The Seriality Gap in Video Diffusion Models

arXiv:2607.13031v1 Announce Type: cross Abstract: When one ball strikes another, then another, video models should predict the consequences of each bounce. In controlled experiments on multi-ball hard

The Spectrum Is Not Enough: When Context Helps Time-Series Forecasting

arXiv:2607.13006v1 Announce Type: new Abstract: A growing family of indices scores how predictable a series is from its spectrum. Practitioners increasingly read these scores as answering a different

Toward Metaphor-Fluid Conversation Design for Voice User Interfaces

arXiv:2502.11554v3 Announce Type: replace-cross Abstract: Metaphors play a critical role in shaping user experiences with Voice User Interfaces (VUIs), yet existing designs often rely on static, human

Towards Vision-Free CIR: Attribute-Augmented Scoring and LLM-Based Reranking for Zero-Shot Composed Image Retrieval

arXiv:2607.12621v1 Announce Type: new Abstract: Recent work has shown that 'Vision-Free'' approaches (representing images as text) can be effective for standard image retrieval tasks. However, it rema

Traceback Translators Against Forgetting in Continual Fake Speech Detection

arXiv:2607.12569v1 Announce Type: cross Abstract: Fake speech detectors are increasingly challenged by the development of new and more accurate generative models. To cope with this problem, continual

Translation as a Computationally Efficient Bridge: Feasibility of English BERT for Low-Resource Languages

arXiv:2607.12612v1 Announce Type: new Abstract: BERT models have revolutionised Natural Language Processing (NLP) through their ability to process unstructured text across diverse domains. However, de

Uncertainty-Aware Multi-Source Retinal Fluid Segmentation in OCT

arXiv:2607.12212v1 Announce Type: cross Abstract: Measuring retinal fluid from optical coherence tomography (OCT) drives treatment decisions in macular disease, but manual annotation is slow and segme

Understanding Structured Health Data through Interaction-Aware Mixture-of-Experts

arXiv:2607.12255v1 Announce Type: new Abstract: We study interaction-aware mixture-of-experts for post-stroke rigidity prediction using multi-level views of structured health records. Despite minimal

UniMedSeg: Unified In-Context Learning for Multi-Paradigm 2D/3D Medical Image Segmentation

arXiv:2607.12896v1 Announce Type: new Abstract: Medical image segmentation foundation models are expected to generalize across diverse clinical scenarios, yet existing universal methods remain fragmen

Virtual Chromoendscopy with Tunable Visibility Enhancement

arXiv:2607.12416v1 Announce Type: new Abstract: Chromoendoscopy (CE) is a common clinical practice that sprays indigo carmine blue dye onto the gastric surface to improve the visibility of gastric les

Visual Access Boundaries in Vision-Language Model Reasoning

arXiv:2607.12815v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting is widely used as a test-time scaling strategy for Vision-Language Models (VLMs), but it remains unclear what is extend

Visual Species Recognition with Large Multimodal Models as Post-Hoc Correctors

arXiv:2512.15748v2 Announce Type: replace-cross Abstract: Visual Species Recognition (VSR) is a fundamental task in scientific disciplines that require species-level identification, including ecology,

We scaled a robot model natively to 8,000 timesteps of context, 5 minutes worth of muscle memory, with constant inference cost. Robot polici…

We scaled a robot model natively to 8,000 timesteps of context, 5 minutes worth of muscle memory, with constant inference cost. Robot policies used to live their lives a few frames at a time (< 0.1 se

researchjim-fan--x

Weakly Supervised Spatio-Temporal Candidate Discovery of Dairy Farm Sites from Seasonal Satellite Imagery

arXiv:2607.12748v1 Announce Type: cross Abstract: Farm site discovery from satellite imagery is a spatiotemporal candidate ranking problem because farm evidence is distributed across pasture, field bo

1) If you haven't read AI as Normal Technology, these annotated slides are probably the easiest way to get a high-level overview. https://ww…

1) If you haven't read AI as Normal Technology, these annotated slides are probably the easiest way to get a high-level overview. https://www.cs.princeton.edu/~arvindn/talks/icml-2026-annotated-slides

researchyann-lecun--x

14 Jul 2026

Model Releases

Google named a Leader in the 2026 IDC MarketScape for Worldwide Foundation Model Software

model-releasesgoogle-cloud-ai

For years, we’ve built with a clear priority: putting the practical needs of the enterprise first. Long before generative AI dominated the headlines, we were focused on building the global infrastruct

14 Jul 2026

🤖 Un robot français en seulement 9 mois ! Rémi Cadene, ancien de Tesla AI et Hugging Face, explique comment son équipe veut faire des robot…

🤖 Un robot français en seulement 9 mois ! Rémi Cadene, ancien de Tesla AI et Hugging Face, explique comment son équipe veut faire des robots un levier pour la logistique, la réindustrialisation et, de

researchyann-lecun--x

14 Jul 2026

Tutorials

Everyone keeps asking me how to build a second brain or an LLM wiki. Here is the easiest setup I have found. I took my Wiki Builder skill, i…

Everyone keeps asking me how to build a second brain or an LLM wiki. Here is the easiest setup I have found. I took my Wiki Builder skill, installed it into HyperAgent (@hyperagentapp) as a reusable s

tutorialsdair-ai--x

13 Jul 2026

Language models and coding agents are great, but there is more to life, and more to AI, than just LLM agents.