Knowledge catalogue
arXiv:2606.29887v1 Announce Type: new Abstract: In real-world applications, guardrails are often expected to identify unsafe user-model interactions according to application-specific safety policies,
arXiv:2606.30244v1 Announce Type: new Abstract: Referring Remote Sensing Image Segmentation (RRSIS) seeks to localize and segment the target object or region specified by a natural language expression
arXiv:2606.29171v1 Announce Type: cross Abstract: While existing data attribution methods can identify which training examples build specific mechanistic circuits, they cannot explain how training dat
arXiv:2606.29575v1 Announce Type: cross Abstract: Recent advances in speech separation (SS) have led to compact front-end models with small parameter sizes, yet their high computational cost remains a
arXiv:2606.30574v1 Announce Type: new Abstract: Many modern generative modeling methods, including diffusion models, normalizing flows, and flow matching, estimate transport maps or plans between dist
arXiv:2606.29933v1 Announce Type: new Abstract: The alignment of language models is typically studied through the lens of capability benchmarks, but the dynamics of how models change during post-train
arXiv:2606.29375v1 Announce Type: new Abstract: Medical large language models are commonly adapted with a fixed low-rank budget, even though medical questions differ substantially in confidence, clini
arXiv:2606.30332v1 Announce Type: new Abstract: Recent advances in diffusion models have shown impressive performance in controllable image generation and dense prediction tasks. However, existing app
arXiv:2606.28666v1 Announce Type: cross Abstract: Agent-based AI has enabled the automation of tasks by exposing application tools and resources to large language models (LLMs). However, to improve sc
arXiv:2606.28899v1 Announce Type: new Abstract: Accurate 6-DoF object pose estimation is fundamental to robotic manipulation, yet vision-based methods often fail under occlusion, poor lighting, and re
arXiv:2606.27886v1 Announce Type: new Abstract: Recent advances in Human Activity Recognition (HAR) from wearable sensors have shown that multi-modal deep learning models consistently outperform their
arXiv:2510.01718v2 Announce Type: replace Abstract: Attention is a core operation in large language models (LLMs). We present BD Attention (BDA), a lossless algorithmic reformulation of attention. BDA
Alibaba allegedly ran 28.8 million fraudulent API exchanges across 25,000 fake accounts to steal Claude's intelligence. If confirmed, it's the largest AI model theft ever attempted. The same week, the
arXiv:2606.27855v1 Announce Type: cross Abstract: Deep learning models for surface electromyography (sEMG) can benefit substantially from subject-specific (re-)calibration, since no sufficiently large
Claude models are now generally available through Microsoft Foundry on Azure infrastructure, providing Azure customers access to Claude Opus 4.8 and Claude Haiku 4.5. This integration allows enterpris
Welcome to the second Cloud CISO Perspectives for June 2026. Today, we’re discussing how we use AI to chart a path to autonomous software development lifecycle security.As with all Cloud CISO Perspect
arXiv:2606.20493v2 Announce Type: replace-cross Abstract: When large language models serve as evaluators in multi-agent systems, their strategy preferences -- whether induced by explicit prompts or by
arXiv:2606.27688v1 Announce Type: cross Abstract: In financial forecasting, predictive performance depends not only on which model is trained, but also on how the trained model is deployed. We study t
arXiv:2606.28225v1 Announce Type: new Abstract: Temporal link prediction is usually evaluated by predictive performance on unseen edges, but in probabilistic temporal graphs this criterion can conflat
arXiv:2603.09731v3 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) are increasingly considered as a foundation for embodied agents, yet it remains unclear whether they
arXiv:2606.27378v1 Announce Type: new Abstract: We introduce an axiomatic evaluation framework for latent thought representations in LLMs, comprising metrics that are independent of downstream benchma
arXiv:2606.28011v1 Announce Type: cross Abstract: We propose an agentic Large Language Model (LLM) framework for active Fault-Tolerant Control (FTC) that transforms fault detection outputs into constr
arXiv:2511.11266v4 Announce Type: replace Abstract: Vision-language models have recently emerged as promising planners for autonomous driving, where success hinges on topology-aware reasoning over spa
arXiv:2602.10238v2 Announce Type: replace Abstract: The growing size of Large Language Models (LLMs) makes efficient inference challenging, primarily due to the memory demands of the autoregressive Ke
arXiv:2606.27880v1 Announce Type: new Abstract: Unified fashion generation integrates tasks like virtual try-on and garment reconstruction into a single model to reduce task-specific adaptation costs.
arXiv:2606.27785v1 Announce Type: cross Abstract: Training-free compression methods for large language models (LLMs) often use calibration data to guide compression decisions. ROCKET, a recent method
arXiv:2606.27793v1 Announce Type: cross Abstract: Long-context language models suffer from position bias, where information in middle positions is underutilized. Attention Sorting addresses this by it
arXiv:2510.18874v3 Announce Type: replace-cross Abstract: Adapting language models (LMs) to new tasks via post-training carries the risk of degrading existing capabilities -- a phenomenon classically
arXiv:2606.27909v1 Announce Type: cross Abstract: Theory-of-mind evaluations of large language models typically use dyadic social-deduction games, where every observable cue points to a single hidden
arXiv:2606.27669v1 Announce Type: new Abstract: Search agents powered by large language models (LLMs) are increasingly used to solve complex information-seeking tasks, requiring multi-step retrieval a
arXiv:2606.27708v1 Announce Type: new Abstract: Adapting a foundation vision-language encoder to a specialized retrieval task creates a fundamental tradeoff: gains on the target distribution come at t
China's Zhipu AI (Z.ai) released its open-weight GLM-5.2, and some researchers have claimed that it matches Mythos in certain bug-finding and cybersecurity scenarios. While GLM lags behind models from
Elon Musk turns 55 today. Here are 55 milestones. Age 54: world's first trillionaire Age 54: takes SpaceX public Age 54: SpaceX acquires xAI Age 54: releases Grok 4 Age 53: launches Robotaxi service A
https://huggingface.co/collections/deepseek-ai/deepspec Good guy DeepSeek gives us accelerated models The most interesting one here is Gemma4-12B, I presume vision included. Might be the best local mo
OpenAI has released GPT-5.6 with three variants (Sol, Terra, Luna) in a restricted beta program limited to trusted partners, according to reporting from Latent Space. The restricted access model sugge
arXiv:2606.26457v1 Announce Type: cross Abstract: This paper presents a probabilistic framework for online test-time adaptation problems. In them, a model is trained on labeled data but must adapt to
arXiv:2606.26479v1 Announce Type: cross Abstract: Recent work (2024 to 2026) has converged on a strategy for defending tool-using LLM agents against indirect prompt injection: rather than training the
arXiv:2606.26489v1 Announce Type: new Abstract: News media play a central role in shaping public perceptions of climate change, and whether coverage emphasizes threats or solutions has measurable effe
arXiv:2606.26904v1 Announce Type: cross Abstract: Video reasoning language models implicitly assume that every input frame is equally reliable. This leads to what we term the Blind Trust Problem: unde
arXiv:2606.26620v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have emerged as a powerful tool for decomposing superposed language model representations into sparse and interpretable fea
arXiv:2606.12716v2 Announce Type: replace Abstract: The integration of Large Language Models (LLMs) and Multimodal LLMs (MLLMs) into scientific peer-review workflows introduces novel and significant r
arXiv:2606.21649v2 Announce Type: replace Abstract: Existing embedding models are inherently static: they encode text segments in isolation, ignoring their surrounding context and temporal order. This
arXiv:2606.26923v1 Announce Type: new Abstract: Vision-language models (VLMs) often produce hallucinated or inconsistent outputs, where text and images are not properly aligned. Addressing this issue
Have been taking different local open-weight LLMs for a test drive in different harnesses (Qwen-Code, Codex, Claude Code). 30B Mixture-of-Expert models are kind of a nice sweet spot and can solve chal
arXiv:2606.27295v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models are commonly pretrained on robot demonstrations by jointly mapping visual observations and language instructions to
arXiv:2606.26592v1 Announce Type: cross Abstract: We propose latent-space diffusion posterior sampling (L-DPS), an approximate Bayesian framework for high-dimensional inverse problems governed by part
arXiv:2606.27237v1 Announce Type: new Abstract: Language models (LMs) capture large amounts of factual knowledge applicable to a wide range of tasks, motivating the view of their parameters as a knowl
arXiv:2606.26421v1 Announce Type: new Abstract: State-of-the-art medium-range AI weather models can outperform traditional Numerical Weather Prediction (NWP) but require massive training budgets. This
arXiv:2606.26907v1 Announce Type: new Abstract: While text-to-image (T2I) models have achieved remarkable progress, they struggle with real-world requests that are often underspecified, implicit, or d
arXiv:2606.26947v1 Announce Type: cross Abstract: While personalized image generation has achieved remarkable progress, multi-reference image generation (MRIG) remains a challenging task. Most existin
arXiv:2606.25200v1 Announce Type: new Abstract: The accelerated digitalization of renewable energy smart grids through IoT sensors, AMI, and SCADA systems has significantly expanded the attack surface
arXiv:2507.06457v2 Announce Type: replace Abstract: Transformers face quadratic complexity and memory issues with long sequences, prompting the adoption of linear attention mechanisms using fixed-size
Meta released Harness, an open-source framework for evaluating and benchmarking AI model performance across diverse tasks and datasets. The tool enables standardized testing of language models and aim
arXiv:2606.25174v1 Announce Type: cross Abstract: Field-scale retrieval of surface soil moisture (SM), leaf area index (LAI), and plant height (PH) is essential for precision agriculture, yet it remai
arXiv:2606.25527v1 Announce Type: new Abstract: Online reinforcement learning (RL) agents increasingly depend on knowledge acquired offline to achieve practical efficiency. Originally studied in offli
arXiv:2604.03314v2 Announce Type: replace-cross Abstract: Foundation models have revolutionized AI, but adapting them efficiently for multimodal tasks, particularly in dual-stream architectures compos
arXiv:2512.04554v2 Announce Type: replace Abstract: Document Visual Question Answering (DocVQA) enables end-to-end reasoning grounded on information present in a document input. While recent models ha
arXiv:2606.25488v1 Announce Type: new Abstract: Knowledge Distillation (KD) is widely used to obtain compact models for efficient inference in resource-constrained environments. Yet the computational
arXiv:2606.25782v1 Announce Type: new Abstract: With the widespread adoption of large language models (LLMs) in chatbots and everyday applications, companies increasingly need guardrails that are effe
arXiv:2606.25808v1 Announce Type: cross Abstract: We propose a predict-optimize-explain framework that uses gradient-based sample generation to interpret various portfolio models by identifying macroe