Search: “models”

arXiv:2601.13969v2 Announce Type: replace Abstract: Retrieving evidence for language model queries from knowledge graphs requires balancing broad search across the graph with multi-hop traversal to fo

agentsarxiv-cs-ai

Bridge: Basis-Driven Causal Inference Marries VFMs for Domain Generalization

DGX agent

arXiv:2604.26820v1 Announce Type: new Abstract: Detectors often suffer from degraded performance, primarily due to the distributional gap between the source and target domains. This issue is especiall

model-releasesarxiv-cs-cv

30 Apr 2026

DepthPilot: From Controllability to Interpretability in Colonoscopy Video Generation

arXiv:2604.26232v1 Announce Type: cross Abstract: Controllable medical video generation has achieved remarkable progress, but it still lacks interpretability, which requires the alignment of generated

Edge AI for Automotive Vulnerable Road User Safety: Deployable Detection via Knowledge Distillation

arXiv:2604.26857v1 Announce Type: new Abstract: Deploying accurate object detection for Vulnerable Road User (VRU) safety on edge hardware requires balancing model capacity against computational const

local-aiarxiv-cs-cv

eDySec: A Deep Learning-based Explainable Dynamic Analysis Framework for Detecting Malicious Packages in PyPI Ecosystem

arXiv:2604.26219v1 Announce Type: cross Abstract: The security of open-source software repositories is increasingly threatened by next-gen software supply chain attacks. These attacks include multipha

researcharxiv-cs-lg

Featurising Pixels from Dynamic 3D Scenes with Linear In-Context Learners

arXiv:2604.26488v1 Announce Type: new Abstract: One of the most exciting applications of vision models involve pixel-level reasoning. Despite the abundance of vision foundation models, we still lack r

From Black-Box Confidence to Measurable Trust in Clinical AI: A Framework for Evidence, Supervision, and Staged Autonomy

arXiv:2604.26671v1 Announce Type: cross Abstract: Trust in clinical artificial intelligence (AI) cannot be reduced to model accuracy, fluency of generation, or overall positive user impression. In med

researcharxiv-cs-ai

FutureWorld: A Live Environment for Training Predictive Agents with Real-World Outcome Rewards

arXiv:2604.26733v1 Announce Type: new Abstract: Live future prediction refers to the task of making predictions about real-world events before they unfold. This task is increasingly studied using larg

HealthNLP_Retrievers at ArchEHR-QA 2026: Cascaded LLM Pipeline for Grounded Clinical Question Answering

arXiv:2604.26880v1 Announce Type: new Abstract: Patient portals now give individuals direct access to their electronic health records (EHRs), yet access alone does not ensure patients understand or ac

Multimodal LLMs are not all you need for Pediatric Speech Language Pathology

arXiv:2604.26568v1 Announce Type: new Abstract: Speech Sound Disorders (SSD) affect roughly five percent of children, yet speech-language pathologists face severe staffing shortages and unmanageable c

Naamah: A Large Scale Synthetic Sanskrit NER Corpus via DBpedia Seeding and LLM Generation

arXiv:2604.26456v1 Announce Type: cross Abstract: The digitisation of classical Sanskrit literature is impeded by a scarcity of annotated resources, particularly for Named Entity Recognition. While re

Tutorials

Observable Neural ODEs for Identifiable Causal Forecasting in Continuous Time

arXiv:2604.26070v1 Announce Type: new Abstract: Causal inference in continuous-time sequential decision problems is challenged by hidden confounders. We show that, in latent state-space models with ti

tutorialsarxiv-cs-lg

OMEGA: Optimizing Machine Learning by Evaluating Generated Algorithms

arXiv:2604.26211v1 Announce Type: new Abstract: In order to automate AI research we introduce a full, end-to-end framework, OMEGA: Optimizing Machine learning by Evaluating Generated Algorithms, that

One Word at a Time: Incremental Completion Decomposition Breaks LLM Safety

arXiv:2604.25921v1 Announce Type: new Abstract: Large Language Models (LLMs) are trained to refuse harmful requests, yet they remain vulnerable to jailbreak attacks that exploit weaknesses in conversa

safetyarxiv-cs-cl

Parameterized Quantum Circuits as Feature Maps: Representation Quality and Readout Effects in Multispectral Land-Cover Classification

arXiv:2604.26675v1 Announce Type: cross Abstract: We investigate variational quantum classifiers (VQCs) for land-cover classification from multispectral satellite imagery, adopting a feature-map persp

Industry

pi + qwen3.6 is like FSD 12 We kind of have working self-driving laptops, instead of being puppeted by a demigod from the cloud

This post compares Pi and Qwen 3.6 AI models to Tesla's Full Self-Driving (FSD) technology, suggesting that advanced local AI models enable autonomous computing capabilities similar to self-driving ve

industryclem-delangue--x

Quantum Feature Selection with Higher-Order Binary Optimization on Trapped-Ion Hardware

arXiv:2604.26834v1 Announce Type: cross Abstract: We present a quantum feature-selection framework based on a higher-order unconstrained binary optimization (HUBO) formulation that explicitly incorpor

SafeReview: Defending LLM-based Review Systems Against Adversarial Hidden Prompts

arXiv:2604.26506v1 Announce Type: new Abstract: As Large Language Models (LLMs) are increasingly integrated into academic peer review, their vulnerability to adversarial prompts -- adversarial instruc

researcharxiv-cs-cl

SongBench: A Fine-Grained Multi-Aspect Benchmark for Song Quality Assessment

arXiv:2604.25937v1 Announce Type: cross Abstract: Recent advancements in Text-to-Song generation have enabled realistic musical content production, yet existing evaluation benchmarks lack the professi

SpecTr-GBV: Multi-Draft Block Verification Accelerating Speculative Decoding

arXiv:2604.25925v1 Announce Type: new Abstract: Autoregressive language models suffer from high inference latency due to their sequential decoding nature. Speculative decoding (SD) mitigates this by e

researcharxiv-cs-cl

StratMem-Bench: Evaluating Strategic Memory Use in Virtual Character Conversation Beyond Factual Recall

arXiv:2604.26243v1 Announce Type: cross Abstract: Achieving realistic human-like conversation for virtual characters requires not only a simple memorization and recall of past events, but also the str

Test-Time Safety Alignment

arXiv:2604.26167v1 Announce Type: cross Abstract: Recent work has shown that a model's input word embeddings can serve as effective control variables for steering its behavior toward outputs that sati

safetyarxiv-cs-ai

Uncertainty-Aware Information Pursuit for Interpretable and Reliable Medical Image Analysis

arXiv:2506.16742v3 Announce Type: replace Abstract: To be adopted in safety-critical domains like medical image analysis, AI systems must provide human-interpretable decisions. Variational Information

safetyarxiv-cs-cv

We've partnered with @OpenAI to offer GPT-5.5 in Devin at 50% off through May 14 starting today.

model-releasescognition-ai--x

We've partnered with @OpenAI to offer GPT-5.5 in Devin at 50% off through May 14 starting today. GPT-5.5 is now available in Devin as an Agent Preview! GPT-5.5 has set a new bar for what's possible wi

Adaptable phase retrieval for coherent transition radiation spectroscopy based on differentiable physics information

arXiv:2604.25489v1 Announce Type: cross Abstract: Coherent transition radiation (CTR) spectroscopy is a critical diagnostic for characterizing the longitudinal structure of relativistic electron bunch

Tools

AI evals are becoming the new compute bottleneck

As AI models grow larger and more capable, the computational cost and time required to evaluate them has become a significant limiting factor in development, potentially surpassing training compute as

toolshugging-face

Applications

Bayesian Inverse Transition Learning: Learning Dynamics From Near-Optimal Trajectories

arXiv:2411.05174v2 Announce Type: replace Abstract: We consider the problem of estimating the transition dynamics T^* from near-optimal expert trajectories in the context of offline model-based reinfo

applicationsarxiv-cs-lg

Bug-Report-Driven Fault Localization: Industrial Benchmarking and Lesson Learned at ABB Robotics

arXiv:2604.25700v1 Announce Type: cross Abstract: Software quality assurance remains a major challenge in industrial environments, where large-scale and long-lived systems inevitably accumulate defect

local-aiarxiv-cs-lg

CAN-QA: A Question-Answering Benchmark for Reasoning over In-Vehicle CAN Traffic

arXiv:2604.24935v1 Announce Type: cross Abstract: The Controller Area Network (CAN) is a safety-critical in-vehicle communication protocol that lacks built-in security mechanisms, making intrusion det

CGU-ILALab at FoodBench-QA 2026: Comparing Traditional and LLM-based Approaches for Recipe Nutrient Estimation

arXiv:2604.25774v1 Announce Type: new Abstract: Accurate nutrient estimation from unstructured recipe text is an important yet challenging problem in dietary monitoring, due to ambiguous ingredient te

Cheaper, Better, Faster, Stronger: Robust Text-to-SQL without Chain-of-Thought or Fine-Tuning

arXiv:2505.14174v2 Announce Type: replace Abstract: LLMs are effective at code generation tasks like text-to-SQL, but is it worth the cost? Many state-of-the-art approaches use non-task-specific LLM t

Agents

DeepAgents Deploy is great, you get - a fully open agent harness (no hidden stuff, inspect everything) - managed infra - can use any cocktai…

DeepAgents Deploy is great, you get - a fully open agent harness (no hidden stuff, inspect everything) - managed infra - can use any cocktail of models including Open Models - and everything is traced

agentsharrison-chase--x

Edge-Cloud Collaborative Reconstruction via Structure-Aware Latent Diffusion for Downstream Remote Sensing Perception

arXiv:2604.25319v1 Announce Type: new Abstract: The exponential surge in high-resolution remote sensing data faces a severe bottleneck in satellite-to-ground transmission. Limited downlink bandwidth f

Enhancing Financial Report Question-Answering: A Retrieval-Augmented Generation System with Reranking Analysis

arXiv:2603.16877v2 Announce Type: replace Abstract: Financial analysts face significant challenges extracting information from lengthy 10-K reports, which often exceed 100 pages. This paper presents a

Free Registration & $20K Prize Pool: 2nd MLC-SLM Challenge 2026 on Multilingual Speech LLMs [N]

researchr-machinelearning

The 2nd Multilingual Conversational Speech Language Model (MLC-SLM) Challenge is an open research competition inviting teams worldwide to participate , featuring free registration with a $20K prize po

GPT-Image-2 in the Wild: A Twitter Dataset of Self-Reported AI-Generated Images from the First Week of Deployment

model-releasesarxiv-cs-cv

arXiv:2604.25370v1 Announce Type: new Abstract: The release of GPT-image-2 by OpenAI marks a watershed moment in AI-generated imagery: the boundary between photographic reality and synthetic content h

IAM: Identity-Aware Human Motion and Shape Joint Generation

arXiv:2604.25164v1 Announce Type: new Abstract: Recent advances in text-driven human motion generation enable models to synthesize realistic motion sequences from natural language descriptions. Howeve

Interactive Episodic Memory with User Feedback

arXiv:2604.24893v1 Announce Type: new Abstract: In episodic memory with natural language queries (EM-NLQ), a user may ask a question (e.g., 'Where did I place the mug?') that requires searching a long

safetyarxiv-cs-cv

Learning from Medical Entity Trees: An Entity-Centric Medical Data Engineering Framework for MLLMs

arXiv:2604.25296v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have shown transformative potential in medical applications, yet their performance is hindered by conventional

safetyarxiv-cs-cl

Measuring the stability and plasticity of recommender systems

arXiv:2508.03941v3 Announce Type: replace-cross Abstract: The typical offline protocol to evaluate recommendation algorithms is to collect a dataset of user-item interactions and then use a part of th

researcharxiv-cs-lg

MTPano: Multi-Task Panoramic Scene Understanding via Label-Free Integration of Dense Prediction Priors

arXiv:2602.05330v2 Announce Type: replace Abstract: Comprehensive panoramic scene understanding is critical for immersive applications, yet it remains challenging due to the scarcity of high-resolutio

OmniAlpha: Aligning Transparency-Aware Generation via Multi-Task Unified Reinforcement Learning

arXiv:2511.20211v2 Announce Type: replace Abstract: Transparency-aware generation requires modeling not only RGB appearance but also alpha-based opacity and cross-layer composition, which are essentia

local-aiarxiv-cs-cv

On Halting vs Converging in Recurrent Graph Neural Networks

arXiv:2604.25551v1 Announce Type: new Abstract: Recurrent Graph Neural Networks (RGNNs) extend standard GNNs by iterating message-passing until some stopping condition is met. Various RGNN models have

local-aiarxiv-cs-lg

Origin-Destination Demand Prediction: An Urban Radiation and Attraction Perspective

arXiv:2412.00167v2 Announce Type: replace Abstract: In recent years, origin-destination (OD) demand prediction has gained significant attention for its profound implications in urban development. Exis

ResetEdit: Precise Text-guided Editing of Generated Image via Resettable Starting Latent

arXiv:2604.25128v1 Announce Type: new Abstract: Recent advances in diffusion models have enabled high-quality image generation, leading to increasing demand for post-generation editing that modifies l

safetyarxiv-cs-cv

Residual-loss Anomaly Analysis of Physics-Informed Neural Networks: An Inverse Method for Change-point Detection in Nonlinear Dynamical Systems with Regime Switching

arXiv:2604.25655v1 Announce Type: cross Abstract: Nonlinear dynamical systems with regime transitions are typically described by ordinary differential equations with jumping parameters parameters. Tra

Towards Robust Deep Learning-based Rumex Obtusifolius Detection from Drone Images

arXiv:2604.25316v1 Announce Type: new Abstract: Domain adaptation (DA) addresses the challenge of transferring a machine learning model trained on a source domain to a target domain with a different d

Transformed my office vibe with FLUX.2 Klein 9B with LORA — before/after [workflow link provided]

local-air-stablediffusion

I need to check the actual content of this post to provide an accurate summary. FLUX.2 [klein] 9B is a 9 billion parameter image generation model capable of generating images from text descriptions an