Search: “models”

arXiv:2509.23248v3 Announce Type: replace Abstract: The rapid advancement of large language models (LLMs) has enabled an emergence of agentic artificial intelligence (AI) with powerful reasoning and a

agentsarxiv-cs-ai

RSTR: Reducing SpatioTemporal Redundancy in Diffusion Transformers

DGX agent

arXiv:2512.14096v2 Announce Type: replace Abstract: Diffusion Transformers (DiTs) have achieved remarkable success in image generation, yet their deployment is hindered by high computational costs. We

model-releasesarxiv-cs-cv

11 Jun 2026

Schutzen: Evaluating LLM Safety in Bulgarian and German Contexts

arXiv:2606.11316v1 Announce Type: new Abstract: Large language models are increasingly deployed across professional domains, bringing hard-to-predict risks, including the generation of harmful or disr

safetyarxiv-cs-cl

Semantic search for 100M+ galaxy images using AI-generated captions

arXiv:2512.11982v2 Announce Type: replace-cross Abstract: Finding scientifically interesting phenomena through slow manual labeling campaigns severely limits our ability to explore the billions of gal

researcharxiv-cs-ai

Semantic Segmentation of Node and Edge Diagrams for Assistive Technology

arXiv:2606.11320v1 Announce Type: new Abstract: In this paper, we present a novel set of related models for semantic segmentation of node-link diagrams. These diagrams are frequently used to represent

researcharxiv-cs-cv

Simplicity Suffices for Parameter Noise Injection in Stochastic Gradient Descent

arXiv:2606.12054v1 Announce Type: new Abstract: Injecting noise into the optimization process is a well-established technique for improving the training and generalization of deep neural networks. Yet

SirenFNO: Efficient and Full Frequency Learning of Fourier Neural Operators

arXiv:2606.11518v1 Announce Type: cross Abstract: Fourier neural operators (FNOs) are effective and efficient surrogates for approximating solutions of PDEs and generalize across discretizations. Howe

SoftMatcha 2: A Fast and Soft Pattern Matcher for Trillion-Scale Corpora

model-releasesarxiv-cs-cl

arXiv:2602.10908v2 Announce Type: replace Abstract: We present SoftMatcha 2, an ultra-fast and flexible search algorithm that enables search over trillion-scale natural language corpora in under 0.3 s

SPEA2^+: Improved Density Estimation in SPEA2 with Provable Runtime Guarantees

arXiv:2606.12382v1 Announce Type: cross Abstract: The Strength Pareto Evolutionary Algorithm 2 (SPEA2) is a popular and prominent evolutionary algorithm for solving multi-objective optimisation proble

Substrate Asymmetry in User-Side Memory: A Diagnostic Framework

arXiv:2606.11712v1 Announce Type: cross Abstract: User-side memory in LLMs is typically scored as a single 'personalization' capability: given a user's history, is the output more user-aware? We show

SVoT: State-aware Visualization-of-Thought for Spatial Reasoning via Reinforcement Learning

arXiv:2606.11770v1 Announce Type: new Abstract: Spatial reasoning remains a challenge for Multimodal Large Language Models (MLLMs), as it requires reliable multi-hop inference over both intermediate s

safetyarxiv-cs-ai

SwiftCTS: Fast Cross-Design Prediction and Pareto Optimization of Clock Tree Metrics via Few-Shot Calibration

arXiv:2606.11348v1 Announce Type: new Abstract: Clock Tree Synthesis (CTS) is a computationally expensive stage in the physical design flow, requiring iterative EDA tool invocations to navigate a vast

Tac-DINO: Learning Vision-Tactile Features with Patch Alignment

model-releasesarxiv-cs-cv

arXiv:2606.12069v1 Announce Type: new Abstract: Touch is the primary medium through which humans interact with the environment. Currently, tactile learning mainly focuses on image-level pretraining or

Time-multiplexed layer reuse for physical neural networks

arXiv:2511.00044v3 Announce Type: replace Abstract: Physical neural networks (PNNs) are promising candidates for next-generation computing, but existing demonstrations remain several orders of magnitu

Very pleased to hear Anthropic have walked back this policy https://simonwillison.net/2026/Jun/11/anthropic-walks-back-policy/

Very pleased to hear Anthropic have walked back this policy https://simonwillison.net/2026/Jun/11/anthropic-walks-back-policy/ BREAKING NEWS: Anthropic's latest model will NOT help you if it thinks yo

safetyjeremy-howard--x

When Context Returns: Toward Robust Internalization in On-Policy Distillation

arXiv:2606.11627v1 Announce Type: cross Abstract: Recent work has shown that on-policy distillation can internalize privileged context, such as system prompts or task hints, into a student model so th

safetyarxiv-cs-ai

When Poison Fails After Retrieval: Revisiting Corpus Poisoning under Chunking and Reranking Pipelines

arXiv:2606.11265v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems are vulnerable to corpus poisoning attacks that manipulate downstream model outputs through malicious kno

researcharxiv-cs-ai

Wordle 1,817 3/6 ⬛⬛🟨⬛⬛ 🟨🟨🟨🟩⬛ 🟩🟩🟩🟩🟩

model-releasesanthropic--x

This post documents a Wordle puzzle solution (puzzle #1,817) completed in 3 attempts out of 6 allowed guesses, showing the progression of letter feedback (gray for incorrect letters, yellow for correc

A complementary study on PlanGPT: Evaluation with defined Performance Metrics and comparison with a planner

arXiv:2606.10489v1 Announce Type: new Abstract: Automated Planning is a subfield of Artificial Intelligence (AI) where the main objective is generating a sequence of actions, known as a plan, that hel

A Large Scale Open-Source Image and Video Dataset for Robust Wildfire Detection and Classification

model-releasesarxiv-cs-cv

arXiv:2606.10174v1 Announce Type: new Abstract: Wildfire detection and monitoring are critical for mitigating fire spread and reducing environmental and infrastructural damage. In this work, we introd

A Survey of Robotic Navigation and Manipulation with Physics Simulators in the Era of Embodied AI

arXiv:2505.01458v2 Announce Type: replace-cross Abstract: Navigation and manipulation are core capabilities in Embodied AI, but training agents to perform them directly in the real world is costly, ti

Tutorials

A Unifying Lens on Supervised Fine-Tuning Through Target Distribution Design

arXiv:2606.11189v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) typically maximizes the likelihood of every token in a demonstrated trajectory. However, an observed token can be non-uni

tutorialsarxiv-cs-ai

Agents

ActiveMem: Distributed Active Memory for Long-Horizon LLM Reasoning

arXiv:2606.10532v1 Announce Type: new Abstract: Memory is essential for enabling large language model (LLM) agents to handle long-horizon reasoning tasks. Existing memory mechanisms are largely centra

agentsarxiv-cs-ai

Agentic Hybrid RAG for Evidence-Grounded Muon Collider Analysis

arXiv:2606.10381v1 Announce Type: cross Abstract: Muon collider research spans accelerator physics, detector instrumentation, and high-energy phenomenology, with relevant evidence scattered across a r

AgniNav: Configuration-Driven Cross-Embodiment Local Planning for Robot Navigation

model-releasesarxiv-cs-ro

arXiv:2606.10903v1 Announce Type: new Abstract: Monocular local navigation is attractive for lightweight robots, but existing vision-based policies often couple perception to a specific body, camera h

An adaptive framework for the axisymmetric pulsar magnetosphere using physics-informed Kolmogorov-Arnold networks

arXiv:2606.10686v1 Announce Type: cross Abstract: The pulsar magnetosphere has only recently been addressed using Physics-Informed Neural Networks (PINNs), by deploying a domain-decomposition approach

and the video for reference: https://x.com/ClaudeDevs/status/2064399512664526853 (I didnt get to use the updated designs in time)

and the video for reference: https://x.com/ClaudeDevs/status/2064399512664526853 (I didnt get to use the updated designs in time) Claude Fable 5 changed how we work on the Claude Code team day to day.

model-releasesthariq--x

Announcing the Gemma challenge! Google, Hugging Face, and the open-source AI community choose to empower AI builders rather than sabotage th…

model-releasesclem-delangue--x

Announcing the Gemma challenge! Google, Hugging Face, and the open-source AI community choose to empower AI builders rather than sabotage them. Fun to see the Hub becoming the platform where agents co

Anomaly Detection and Root Cause Analysis for Microservice Systems

arXiv:2606.09942v1 Announce Type: cross Abstract: Microservice systems are widely used to build cloud applications, yet their complexity makes failures inevitable, degrading user experience and causin

Anthropic secretly limiting Claude's usefulness for LLM development strengthens the argument that Anthropic is using AI safety to justify monopolistic behavior (Dean W. Ball/@deanwball)

Dean W. Ball / @deanwball: Anthropic secretly limiting Claude's usefulness for LLM development strengthens the argument that Anthropic is using AI safety to justify monopolistic behavior — My last obs

model-releasestechmeme

Industry

anyone hiring witches to save training runs

Emad Mostaque humorously posted on X asking if anyone was hiring 'witches' to save training runs, likely referencing the challenges and failures that occur during large-scale AI model training process

industryemad-mostaque--x

at Code w/ Claude Tokyo! say hi if you see me around

Thariq posted about attending a coding event or workshop featuring Claude in Tokyo and invited others to say hello if they encountered him there. The post appears to be a social announcement about his

model-releasesthariq--x

Automatic Labelling for Low-Light Pedestrian Detection

arXiv:2507.02513v4 Announce Type: replace Abstract: Pedestrian detection in RGB images is a key task in pedestrian safety, as the most common sensor in autonomous vehicles and advanced driver assistan

safetyarxiv-cs-cv

Boosting Graph Robustness Against Backdoor Attacks: An Over-Similarity Perspective

arXiv:2502.01272v3 Announce Type: replace Abstract: Graph Neural Networks (GNNs) have achieved notable success in tasks such as social and transportation networks. However, recent studies have highlig

Applications

CITRAS: Covariate-Informed Transformer for Time Series Forecasting

arXiv:2503.24007v4 Announce Type: replace-cross Abstract: In time series forecasting, covariates represent external factors that influence target variables. Some covariates are observable only in the

applicationsarxiv-cs-ai

ClusBench: The Clustering Benchmark Data Resource You've All Been Waiting For (?)

arXiv:2606.10673v1 Announce Type: cross Abstract: Although some very common test beds exist for assessing the performance of clustering methods, large scale benchmarking is typically limited to relati

Applications

Co-GLANCE: Uncertainty-Aware Active Perception for Heterogeneous Robot Teaming

arXiv:2606.09919v1 Announce Type: cross Abstract: Perceptual uncertainty is a central challenge for heterogeneous robot teams operating in unstructured outdoor environments, where no single viewpoint

applicationsarxiv-cs-ai

CollabSkill: Evaluating Human-Agent Collaboration On Real-World Tasks

arXiv:2606.09833v1 Announce Type: cross Abstract: AI agents are reshaping the workspace, leading to drastic change of how humans work. Despite the considerable potential of human-agent collaboration b

Constructing coherent spatial memory in LLM agents through graph rectification

arXiv:2510.04195v2 Announce Type: replace Abstract: Given a map description through global traversal navigation instructions, an LLM can often infer the implicit spatial layout and answer user queries

Continuous Neural Reparameterization as a Deep Geometric Prior for Robust Fixed-Chart UV Repair

model-releasesarxiv-cs-cv

arXiv:2606.10050v1 Announce Type: cross Abstract: Traditional UV unwrapping relies on direct optimization of geometric distortion energies and can fail through invalid initialization, local minima, or

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP

arXiv:2601.19210v2 Announce Type: replace Abstract: Vision-language models (VLMs) such as CLIP have demonstrated remarkable zero-shot generalization, yet remain highly vulnerable to adversarial exampl

safetyarxiv-cs-cv

ConvMemory v2: A Recall-Preserving Top-10 Evidence Reranker for Conversational Memory Retrieval

model-releasesarxiv-cs-cl

arXiv:2606.10842v1 Announce Type: new Abstract: We describe ConvMemory v2, an opt-in token-evidence reranker that sits after the lightweight ConvMemory v1 reranker and reorders only v1's protected top

Local Ai

Currently best way of image upscaling and restoration as of may 2026

local-air-stablediffusion

As of May 2026, image upscaling tools split into two main categories: true-to-source models optimized for photo restoration, and creative reimaginers designed for AI art. Leading options include Topaz

datasette-agent 0.2a0

model-releasessimon-willison

Release: datasette-agent 0.2a0 Highlights from the release notes: Tools can now ask the user questions mid-execution. Tools that declare a context parameter receive a ToolContext object, and await con

Decision-Making under Combinatorial Risk

arXiv:2606.10092v1 Announce Type: new Abstract: Decision-making under risk is typically studied through single-shot lottery choices. Yet many real decisions involve combinatorial risk, where risk aris

researcharxiv-cs-lg

Detecting Knowledge Gaps from Conversational AI Interactions Using Curriculum Prerequisite Graphs

arXiv:2606.10736v1 Announce Type: cross Abstract: Large online courses generate thousands of student questions directed at conversational AI teaching assistants, yet these interaction logs remain larg

Dexterous Point Policy: Learning Point-based Dexterous Hand Policies from Human Demonstrations

arXiv:2606.10614v1 Announce Type: cross Abstract: Robotic foundation models pre-trained on human demonstration videos have shown promise, but a significant embodiment gap remains when the resulting po

safetyarxiv-cs-cv

Discovering Interpretable Multi-Parameter Control Policies for Evolutionary Algorithms Using Deep Reinforcement Learning

arXiv:2606.10129v1 Announce Type: new Abstract: While deep Reinforcement Learning (deep-RL) has been increasingly applied to parameter control in evolutionary algorithms, rigorous theoretical analysis