All entries

One Click per Cell Type Suffices: Training-free Group Interaction for Cell Instance Segmentation

arXiv:2605.29429v1 Announce Type: new Abstract: Cell instance segmentation models trained on cell-specific datasets suffer severe performance drops on out-of-distribution cell types, while interactive

researcharxiv-cs-cv

One Mask to Rule Them All: On Hidden Facts after Editing and How to Find Them

DGX agent

arXiv:2605.28839v1 Announce Type: new Abstract: Knowledge editing methods such as ROME and MEMIT update factual associations in transformer models by modifying MLP weights. While evaluated mainly by o

tutorialsarxiv-cs-lg

29 May 2026

Online Fair Division with Additional Information

arXiv:2505.24503v3 Announce Type: replace-cross Abstract: We study the problem of fairly allocating indivisible goods to agents in an online setting, where goods arrive sequentially and must be alloca

safetyarxiv-cs-ai

OOD-GraphLLM: Graph Large Language Model for Out-of-Distribution Generalized Drug Synergy Prediction

model-releasesarxiv-cs-lg

arXiv:2605.30247v1 Announce Type: new Abstract: Drug synergy prediction (DSP) aims to identify efficacious drug combinations under various cellular contexts with different targets. However, the contin

open models are having a moment!

open models are having a moment! The latest finding in the LangSmith Signal: Open Models are having a moment. 1 in 3 AI teams ran an open-weights model in April 2026, up from 1 in 5 nine months ago. T

agentsharrison-chase--x

open models will become a huge force for coding.

open models will become a huge force for coding. The latest finding in the LangSmith Signal: Open Models are having a moment. 1 in 3 AI teams ran an open-weights model in April 2026, up from 1 in 5 ni

agentsharrison-chase--x

Open Problem: Separating Geometric and Algorithmic Compression via Cayley-Table Completion

arXiv:2605.29885v1 Announce Type: new Abstract: Modern statistical learning theory and deep learning characterize generalization primarily in terms of continuous capacity control (e.g., norm-based reg

safetyarxiv-cs-lg

Open Source Browser Agent That Learns and Repeats Workflows

An open-source browser with built-in AI agents that emphasizes privacy and automation, enabling task automation through natural language without coding. The browser supports multiple AI providers incl

agentsr-ollama

Open World Autoencoding Drift Detection with Novel Class Recognition in Tabular Non-stationary Data Streams

arXiv:2605.29834v1 Announce Type: new Abstract: Data stream processing has become a landmark in modern machine learning applications, with concept drifts and novel class appearances posing the primary

Industry

OpenAI says it has briefed the White House on its new biodefense program, which uses GPT-Rosalind to help develop biodefense and pandemic preparedness tools (Maria Curi/Axios)

Maria Curi / Axios: OpenAI says it has briefed the White House on its new biodefense program, which uses GPT-Rosalind to help develop biodefense and pandemic preparedness tools — OpenAI is launching a

industrytechmeme

OpenClawBench: Benchmarking Process-side Anomalies in Real-world Agent Execution Trajectories

arXiv:2605.29253v1 Announce Type: new Abstract: Task success can hide process anomalies in real-world agent executions. An agent may pass the final task oracle while still accumulating unresolved ambi

Local Ai

OpenJarvis: a local-first personal AI is now available to run with Ollama Built by Stanford’s @HazyResearch and Scaling Intelligence labs, a…

OpenJarvis: a local-first personal AI is now available to run with Ollama Built by Stanford’s @HazyResearch and Scaling Intelligence labs, as part of their “Intelligence Per Watt” research into effici

local-aiollama--x

Opir: Efficient Multi-Task Safety Classification for Toxicity, Jailbreaks, Hate Speech, and Harmful Content

arXiv:2605.29659v1 Announce Type: cross Abstract: Real-time safety filtering for large language model (LLM) applications requires classifiers that can detect unsafe prompts, toxic language, jailbreak

Opt-Verifier: Unleashing the Power of LLMs for Optimization Modeling via Dual-Side Verification

arXiv:2605.29556v1 Announce Type: new Abstract: Building mathematical optimization models is critical in operations research (OR), while it requires substantial human expertise. Recent advancements ha

researcharxiv-cs-ai

Optimal Gap-Dependent Regret for Private Stochastic Decision-Theoretic Online Learning

arXiv:2605.29148v1 Announce Type: new Abstract: We study stochastic decision-theoretic online learning with full information and event-level pure differential privacy. A COLT open problem of Hu and Me

Optimal Rates for Differentially Private Hypothesis Testing with E-values

arXiv:2605.28952v1 Announce Type: cross Abstract: E-values have attracted considerable interest in recent years as flexible tools for enabling anytime-valid and adaptive data analysis. Hypothesis test

Optimization and Generation in Aerodynamics Inverse Design

arXiv:2602.03582v3 Announce Type: replace Abstract: Aerodynamic inverse design can improve vehicle and aircraft efficiency, but practical design rarely seeks performance alone: vehicle refinement must

Optimizing Latent Representations for Robust Building Damage Assessment Onboard Earth Observation Satellites

model-releasesarxiv-cs-cv

arXiv:2605.29575v1 Announce Type: new Abstract: Rapid identification of damaged buildings after natural disasters or on war areas is crucial to support emergency response and prioritize interventions.

OptSkills: Learning Generalizable Optimization Skills from Problem Archetypes via Cluster-Based Distillation

arXiv:2605.29829v1 Announce Type: new Abstract: Leveraging Large Language Models (LLMs) to automatically formulate and solve optimization problems from natural language has emerged as an efficient par

Opus 4.8 dropped today. ParseBench results are out. ✅ Slight gains: tables, semantic formatting, layout ⚠️ Slight regressions: charts, conte…

Opus 4.8 dropped today. ParseBench results are out. ✅ Slight gains: tables, semantic formatting, layout ⚠️ Slight regressions: charts, content faithfulness 💰 Slight price/page increase Lots of alpha l

agentsjerry-liu--x

Opus 4.8 is insane, nothing will be the same after this model 💀

Gary Marcus expresses strong enthusiasm about Opus 4.8, suggesting it represents a significant breakthrough in AI capabilities. The post implies the model introduces substantial improvements or novel

safetygary-marcus--x

Order-Agnostic Autoregressive Modelling with Missing Data

arXiv:2605.06355v2 Announce Type: replace Abstract: Order-Agnostic autoregressive models have demonstrated strong performance in deep generative modeling, yet their use in settings with incomplete dat

applicationsarxiv-cs-lg

Orthogonal Concept Erasure for Diffusion Models

arXiv:2605.28902v1 Announce Type: new Abstract: Concept erasure has emerged as a promising approach to mitigate undesired or unsafe content in diffusion models, yet existing methods still face signifi

Orthogonal Negative Guidance in Attention Feature Space for Text-to-Image Generation

arXiv:2605.29390v1 Announce Type: new Abstract: Text-to-image (T2I) models have become increasingly capable of generating high-quality images. Yet, enforcing the explicit absence of a specified object

safetyarxiv-cs-cv

Our users love @StepFun_ai models and this new release packs a punch at a small size. Looking forward to seeing how well it works with Herme…

Our users love @StepFun_ai models and this new release packs a punch at a small size. Looking forward to seeing how well it works with Hermes Agent! ⚡️ Step 3.7 Flash is here: The new frontier is agen

agentsnous-research--x

OVA-IB: One vs All Information Bottleneck for Multi-Modal Alignment

model-releasesarxiv-cs-lg

arXiv:2605.29900v1 Announce Type: new Abstract: Contrastive learning is effective for aligning paired views or modalities, but alignment beyond two modalities remains non-trivial and comparatively und

Overcoming Forgetting in LLM Fine-Tuning with Evolution Strategies

arXiv:2605.30148v1 Announce Type: cross Abstract: Evolution Strategies (ES) has recently emerged as a competitive alternative to reinforcement learning (RL) for large language model (LLM) fine-tuning,

P^2RAG: Efficient Privacy-Preserving RAG Service Supporting Arbitrary Top-k Retrieval

arXiv:2603.14778v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) enables large language models to use external knowledge, but outsourcing the RAG service raises privacy c

Paper Agents, Paper Gains: An Empirical Analysis of DeFi Investment Agents

arXiv:2605.29174v1 Announce Type: new Abstract: DeFi investment agents, systems that use AI for autonomous on-chain trading, have attained over USD 3 billion in combined token valuations since late 20

safetyarxiv-cs-ai

Parallax: Parameterized Local Linear Attention for Language Modeling

arXiv:2605.29157v1 Announce Type: cross Abstract: Large Language Models (LLMs) have become the central paradigm in artificial intelligence, yet the core computational primitive of attention has remain

Parallel Adaptive Multi-Objective Evolutionary Learning of Discretized Bayesian Network Classifiers for Clinical Data

arXiv:2605.29058v1 Announce Type: new Abstract: Bayesian Networks (BNs) are of interest from an explainable AI viewpoint, offering transparent probabilistic models for decision support. Baymex is a re

applicationsarxiv-cs-lg

Parameter-Efficient Subspace Decoupling ViT for Mitigating Multi-Task Negative Transfer in Histological Scoring

model-releasesarxiv-cs-cv

arXiv:2605.29852v1 Announce Type: new Abstract: Histological scoring is essential for diagnosing Non-Alcoholic Fatty Liver Disease (NAFLD), yet its automation remains challenging due to the high annot

ParaTool: Shifting Tool Representations from Context to Parameters

arXiv:2605.29561v1 Announce Type: new Abstract: Tool calling extends large language models (LLMs) by enabling grounded interaction with external executable interfaces, thereby supporting environment-c

PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding

arXiv:2605.30126v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) map visual inputs into dense token sequences, imposing a quadratic computational bottleneck for inference. Elasti

ParCo-SDF: Learning Prior-Free Partial-to-Complete Signed Distance Fields of Deformable Objects

arXiv:2605.29417v1 Announce Type: new Abstract: This study addresses the partial-to-complete geometry reconstruction of deformable objects (DOs) from point-cloud observations toward precise DO manipul

researcharxiv-cs-cv

Parse PDFs at lightspeed (this video is at 1x) Absolute cinema

Parse PDFs at lightspeed (this video is at 1x) Absolute cinema Media We've created the world's fastest PDF parser ⚡️ And it's more accurate than any other open-source, model-free PDF parser out there

agentsjerry-liu--x

Parse PDFs in the browser, or the edge, in milliseconds Our LiteParse WASM package can be literally run anywhere, from cloudflare workers, m…

model-releasesjerry-liu--x

Parse PDFs in the browser, or the edge, in milliseconds Our LiteParse WASM package can be literally run anywhere, from cloudflare workers, mobile runtimes, to the browser. Starter template for Cloudfl

PassNet: Scaling Large Language Models for Graph Compiler Pass Generation

arXiv:2605.29357v1 Announce Type: new Abstract: Modern tensor compilers such as TorchInductor deliver substantial speedups on mainstream models, yet face a systematic performance ceiling on long-tail

PatchBoard: Schema-Grounded State Mutation for Reliable and Auditable LLM Multi-Agent Collaboration

arXiv:2605.29313v1 Announce Type: new Abstract: LLM multi-agent systems often coordinate through natural-language dialogue or loosely structured shared memory, making intermediate state difficult to v

agentsarxiv-cs-cl

Path-Space Mirror Descent for On-Policy Reinforcement Learning under the Generalized Schrodinger Bridge

arXiv:2603.21621v2 Announce Type: replace Abstract: Classical on-policy algorithms such as PPO and mirror descent policy optimization provide stable proximal policy updates through tractable action li

safetyarxiv-cs-lg

Industry

Paxos says the US SEC has approved its registration as a clearing agency, allowing it to provide clearing and settlement services for eligible transactions (Danny Park/The Block)

Danny Park / The Block: Paxos says the US SEC has approved its registration as a clearing agency, allowing it to provide clearing and settlement services for eligible transactions — Quick Take — Paxos

industrytechmeme

PEARL: Training Socratic Tutors with Pedagogically Aligned Reinforcement Learning

arXiv:2605.29582v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown promise as educational tutors, yet effective tutoring requires more than solving problems: it must provide pro

safetyarxiv-cs-cl

Permutation-Invariant Spectral Learning via Dyson Diffusion

arXiv:2510.08535v2 Announce Type: replace-cross Abstract: Diffusion models are central to generative modeling and have been adapted to graphs by diffusing adjacency matrix representations. The challen

safetyarxiv-cs-lg

Persona Conditioning of Brand Recommendations in Retrieval-Augmented Commercial Chat: A Prominence-Stratified Cross-Provider Audit

arXiv:2605.30207v1 Announce Type: new Abstract: The same prompt -- 'best CRM software' -- reaches AI assistants from buyers in widely different contexts: a solo founder, an enterprise VP, a UK SMB own

PersonaAgent: Bridging Memory and Action for Personalized LLM Agents

arXiv:2506.06254v2 Announce Type: replace Abstract: Large Language Model (LLM) empowered agents have recently emerged as advanced paradigms that exhibit impressive capabilities in a wide range of doma

safetyarxiv-cs-ai

Personalized Turn-Level User Conversation Satisfaction Benchmark

arXiv:2605.29711v1 Announce Type: cross Abstract: User satisfaction with AI assistants is highly personalized: the same response may satisfy one user but disappoint another depending on what each user

PhAIL: A Real-Robot VLA Benchmark and Distributional Methodology

model-releasesarxiv-cs-ro

arXiv:2605.29710v1 Announce Type: new Abstract: Real-world evaluation of vision-language-action (VLA) policies still rests on binary success rate at a fixed timeout with N le 25 rollouts per condition

Phantom: Training Robots Without Robots Using Only Human Videos

arXiv:2503.00779v2 Announce Type: replace Abstract: Training general-purpose robots requires learning from large and diverse data sources. Current approaches rely heavily on teleoperated demonstration

researcharxiv-cs-ro