Search: “models”

Tree-Conditioned Edit Flows for Ancestral Sequence Reconstruction

arXiv:2605.04119v1 Announce Type: cross Abstract: Ancestral sequence reconstruction (ASR) aims to infer extinct protein sequences at internal nodes of a phylogenetic tree. Classical ASR methods are ty

7 May 2026

Model Releases

Before Forgetting, Learn to Remember: Revisiting Foundational Learning Failures in LVLM Unlearning Benchmarks

DGX agent

arXiv:2605.03759v1 Announce Type: new Abstract: While Large Vision-Language Models (LVLMs) offer powerful capabilities, they pose privacy risks by unintentionally memorizing sensitive personal informa

model-releasesarxiv-cs-cv

6 May 2026

Coordination as an Architectural Layer for LLM-Based Multi-Agent Systems

arXiv:2605.03310v1 Announce Type: cross Abstract: Multi-agent LLM systems fail in production at rates between 41% and 87%, mostly due to coordination defects rather than base-model capability. Existin

Feature-Augmented Transformers for Robust AI-Text Detection Across Domains and Generators

arXiv:2605.03969v1 Announce Type: new Abstract: AI-generated text is nowadays produced at scale across domains and heterogeneous generation pipelines, making robustness to distribution shift a central

Hello again, everyone! Our latest Qwopus3.6-35B-A3B-v1 is now live, and it is once again breathtaking! Full HF space benchmark showcase and …

model-releasesclem-delangue--x

Hello again, everyone! Our latest Qwopus3.6-35B-A3B-v1 is now live, and it is once again breathtaking! Full HF space benchmark showcase and write-up is in the comments, so you can make conclusions for

PatRe: A Full-Stage Office Action and Rebuttal Generation Benchmark for Patent Examination

arXiv:2605.03571v1 Announce Type: new Abstract: Patent examination is a complex, multi-stage process requiring both technical expertise and legal reasoning, increasingly challenged by rising applicati

Raising the Ceiling: Better Empirical Fixation Densities for Saliency Benchmarking

arXiv:2605.03885v1 Announce Type: new Abstract: Empirical fixation densities, spatial distributions estimated from human eye-tracking data, are foundational to saliency benchmarking. They directly sha

ReCode: Reinforcing Code Generation with Reasoning-Process Rewards

arXiv:2508.05170v3 Announce Type: replace-cross Abstract: In practice, rigorous reasoning is often a key driver of correct code, while Reinforcement Learning (RL) for code generation often neglects op

Sentinel2Cap: A Human-Annotated Benchmark Dataset for Multimodal Remote Sensing Image Captioning

arXiv:2605.03189v1 Announce Type: new Abstract: Image captioning has become an important task in computer vision, enabling models to generate natural language descriptions of visual content. While sev

Sparse Memory Finetuning as a Low-Forgetting Alternative to LoRA and Full Finetuning

arXiv:2605.03229v1 Announce Type: new Abstract: Adapting a pretrained language model to a new task often hurts the general capabilities it already had, a problem known as catastrophic forgetting. Spar

TriBench-Ko: Evaluating LLM Risks in Judicial Workflows

arXiv:2605.03792v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly integrated into legal workflows. However, existing benchmarks primarily address proxy tasks, such as bar e

Research

TsallisPGD: Adaptive Gradient Weighting for Adversarial Attacks on Semantic Segmentation

arXiv:2605.03405v1 Announce Type: new Abstract: Attacking semantic segmentation models is significantly harder than image classification models because an attacker must flip thousands of pixel predict

researcharxiv-cs-cv

AEM: Adaptive Entropy Modulation for Multi-Turn Agentic Reinforcement Learning

model-releasesarxiv-cs-ai

arXiv:2605.00425v1 Announce Type: new Abstract: Reinforcement learning (RL) has significantly advanced the ability of large language model (LLM) agents to interact with environments and solve multi-tu

Ai2 releases MolmoAct 2, enhancing robot intelligence in the real world

model-releasessiliconangle

Seattle-based artificial intelligence research institute Ai2, the Allen Institute for AI, today announced its next-generation open-source foundation artificial intelligence models, aimed at enabling r

Safety

Anticipation-VLA: Solving Long-Horizon Embodied Tasks via Anticipation-based Subgoal Generation

arXiv:2605.01772v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have emerged as a powerful paradigm for embodied intelligence, enabling robots to perform tasks based on natural l

safetyarxiv-cs-lg

BIM Information Extraction Through LLM-based Adaptive Exploration

arXiv:2605.01698v1 Announce Type: new Abstract: BIM models provide structured representations of building geometry, semantics, and topology, yet extracting specific information from them remains remar

Checkerboard: A Simple, Effective, Efficient and Learning-free Clean Label Backdoor Attack with Low Poisoning Budget

arXiv:2605.01298v1 Announce Type: cross Abstract: Backdoor attacks threaten the deep learning supply chain by poisoning a small fraction of the training data so that a model behaves normally on clean

ContextualJailbreak: Evolutionary Red-Teaming via Simulated Conversational Priming

arXiv:2605.02647v1 Announce Type: new Abstract: Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety alignment and elicit harmful responses. A growing body of work sh

Control Reinforcement Learning: Interpretable Token-Level Steering of LLMs via Sparse Autoencoder Features

arXiv:2602.10437v3 Announce Type: replace-cross Abstract: Sparse autoencoders (SAEs) decompose language model activations into interpretable features, but existing methods reveal only which features a

CoSpaDi: Compressing LLMs via Calibration-Guided Sparse Dictionary Learning

arXiv:2509.22075v5 Announce Type: replace Abstract: Post-training compression of large language models (LLMs) often relies on low-rank weight approximations that represent each column of the weight ma

DBLP: Phase-Aware Bounded-Loss Transport for Burst-Resilient Distributed ML Training

arXiv:2605.01989v1 Announce Type: new Abstract: Distributed machine learning (ML) training has become a necessity with the prevalence of billion to trillion-parameter-scale models. While prior work ha

Deep neural networks with Fisher vector encoding for medical image classification

arXiv:2605.01667v1 Announce Type: new Abstract: Orderless encoding methods have shown to improve Convolutional Neural Networks (CNNs) for image classification in the context of limited availability of

Diet Your LLM: Dimension-wise Global Pruning of LLMs via Merging Task-specific Importance Score

arXiv:2603.23985v2 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated remarkable capabilities, but their massive scale poses significant challenges for practical deploymen

Dual-branch Robust Unlearnable Examples

arXiv:2605.01718v1 Announce Type: new Abstract: Unlearnable examples (UEs) aim to compromise model training by injecting imperceptible perturbations to clean samples. However, existing UE schemes exhi

Research

Enhancing Multimodal In-Context Learning via Inductive-Deductive Reasoning

arXiv:2605.02378v1 Announce Type: new Abstract: In-context learning (ICL) allows large models to adapt to tasks using a few examples, yet its extension to vision-language models (VLMs) remains fragile

researcharxiv-cs-cv

Gen-Searcher: Reinforcing Agentic Search for Image Generation

arXiv:2603.28767v2 Announce Type: replace Abstract: Recent image generation models have shown strong capabilities in generating high-fidelity and photorealistic images. However, they are fundamentally

GPT-5.5 Instant: smarter, clearer, and more personalized

GPT-5.5 Instant is OpenAI's faster, more efficient variant of their GPT-5.5 model, designed to deliver improved reasoning and clarity while maintaining lower latency for real-time applications. The mo

model-releasesopenai

Growing Transformers: Modular Composition and Layer-wise Expansion on a Frozen Substrate

arXiv:2507.07129v3 Announce Type: replace-cross Abstract: We study a constrained training regime for decoder-only Transformers in which the token interface is fixed, previously trained dense blocks ar

Human Cognitive Benchmarks Reveal Foundational Visual Gaps in MLLMs

arXiv:2502.16435v4 Announce Type: replace-cross Abstract: Humans develop perception through a bottom-up hierarchy: from basic primitives and Gestalt principles to high-level semantics. In contrast, cu

Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-Tuning

arXiv:2605.01046v1 Announce Type: new Abstract: LoRA adapts large language models (LLMs) by restricting updates to low-rank subspaces of pre-trained weights. While this substantially reduces training

Leveraging Imperfect Medical Data: A Manifold-Consistent Spatio-Temporal Network for Sensor-based Human Activity Recognition

arXiv:2605.00913v1 Announce Type: new Abstract: Sensor-based Human Activity Recognition (HAR) has attracted increasing attention in medical and healthcare monitoring, particularly with the growth of I

Metric Unreliability in Multimodal Machine Unlearning: A Systematic Analysis and Principled Unified Score

arXiv:2605.02206v1 Announce Type: new Abstract: Machine unlearning in Vision-Language Models (VLMs) is required for compliance with the General Data Protection Regulation (GDPR), yet current evaluatio

Planner Matters! An Efficient and Unbalanced Multi-agent Collaboration Framework for Long-horizon Planning

arXiv:2605.02168v1 Announce Type: cross Abstract: Language model (LM)-based agents have demonstrated promising capabilities in automating complex tasks from natural language instructions, yet they con

Selector-Guided Autonomous Curriculum for One-Shot Reinforcement Learning from Verifiable Rewards

arXiv:2605.01823v1 Announce Type: new Abstract: Recently, Reinforcement Learning from Verifiable Rewards (RLVR) has been established as a highly effective technique for augmenting the math reasoning s

Towards High Fidelity Face Swapping: A Comprehensive Survey and New Benchmark

arXiv:2605.00883v1 Announce Type: new Abstract: Face swapping has witnessed significant progress in recent years, largely driven by advances in deep generative models such as GANs and diffusion models

VideoNet: A Large-Scale Dataset for Domain-Specific Action Recognition

arXiv:2605.02834v1 Announce Type: new Abstract: Videos are unique in their ability to capture actions which transcend multiple frames. Accordingly, for many years action recognition was the quintessen

VISTA: Video Interaction Spatio-Temporal Analysis Benchmark

arXiv:2605.01391v1 Announce Type: new Abstract: Existing benchmarks for Vision-Language Models (VLMs) primarily evaluate spatio-temporal understanding on simple single-action videos, closed attribute

When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering

arXiv:2601.19827v3 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) extends large language models (LLMs) beyond parametric knowledge, yet it is unclear when iterative retrieval-re

When RL Meets Adaptive Speculative Training: A Unified Training-Serving System

arXiv:2602.06932v3 Announce Type: replace Abstract: Speculative decoding can significantly accelerate LLM serving, yet most deployments today disentangle speculator training from serving, treating spe

X2SAM: Any Segmentation in Images and Videos

arXiv:2605.00891v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated strong image-level visual understanding and reasoning, yet their pixel-level perception acros

Local Ai

Zero-Shot Confidence Estimation for Small LLMs: When Supervised Baselines Aren't Worth Training

arXiv:2605.02241v1 Announce Type: cross Abstract: How reliably can a small language model estimate its own correctness? The answer determines whether local-to-cloud routing-escalating queries a cheap

local-aiarxiv-cs-cl

InterChart: Benchmarking Visual Reasoning Across Decomposed and Distributed Chart Information

arXiv:2508.07630v2 Announce Type: replace Abstract: We introduce InterChart, a diagnostic benchmark that evaluates how well vision-language models (VLMs) reason across multiple related charts, a task

ML-Agent: Reinforcing LLM Agents for Autonomous Machine Learning Engineering

arXiv:2505.23723v2 Announce Type: replace Abstract: The emergence of large language model (LLM)-based agents has significantly advanced the development of autonomous machine learning (ML) engineering.

Research

The Algorithmic Gaze of Image Quality Assessment: An Audit and Trace Ethnography of the LAION-Aesthetics Predictor

arXiv:2601.09896v4 Announce Type: replace-cross Abstract: Visual generative AI models are trained using a one-size-fits-all measure of aesthetic appeal. However, what is deemed 'aesthetic' is inextric

researcharxiv-cs-cv

ViLegalNLI: Natural Language Inference for Vietnamese Legal Texts

arXiv:2605.00116v1 Announce Type: new Abstract: In this article, we introduce ViLegalNLI, the first large-scale Vietnamese Natural Language Inference (NLI) dataset specifically constructed for the leg

Tutorials

A generalised pre-training strategy for deep learning networks in semantic segmentation of remotely sensed images

arXiv:2604.27704v1 Announce Type: new Abstract: In the segmentation of remotely sensed images, deep learning models are typically pre-trained using large image databases like ImageNet before fine-tune

tutorialsarxiv-cs-cv

1 May 2026

AutoSP: Unlocking Long-Context LLM Training Via Compiler-Based Sequence Parallelism

arXiv:2604.27089v1 Announce Type: new Abstract: Large-language-models (LLMs) demonstrate enormous utility in long-context tasks which require processing prompts that consist of tens to hundreds of tho

1 May 2026

CareGuardAI: Context-Aware Multi-Agent Guardrails for Clinical Safety & Hallucination Mitigation in Patient-Facing LLMs