Dynamic Short Convolutions Improve Transformers
arXiv:2606.03825v1 Announce Type: cross Abstract: Transformers have become the dominant architecture for large language models, largely due to the scalability and flexibility of attention, feed-forwar
Knowledge catalogue
arXiv:2606.03825v1 Announce Type: cross Abstract: Transformers have become the dominant architecture for large language models, largely due to the scalability and flexibility of attention, feed-forwar
arXiv:2604.17220v2 Announce Type: replace-cross Abstract: Modeling coordination among generative agents in complex multi-round decision-making presents a core challenge for AI and operations managemen
arXiv:2606.03770v1 Announce Type: cross Abstract: Large Language Models (LLMs) have become integral to modern applications, yet their deployment remains challenging. Beyond executing the models themse
arXiv:2606.03268v1 Announce Type: new Abstract: Dexterous manipulation learning has long been hindered by the high costs of data and training, as pure reinforcement learning typically requires large-s
arXiv:2606.03804v1 Announce Type: new Abstract: Safe exploration is a key challenge in Reinforcement Learning (RL) that aims to prevent agents from making harmful decisions while exploring their envir
arXiv:2606.02958v1 Announce Type: cross Abstract: Cross-organization language-model adaptation increasingly faces hard governance constraints: in many deployments, device-level model state-parameters,
arXiv:2606.02634v1 Announce Type: cross Abstract: We introduce Echo-POSED, a self-supervised framework for real-time transthoracic echocardiography (TTE) guidance that recommends probe adjustments dir
arXiv:2606.02859v1 Announce Type: cross Abstract: How can a population of agents self-orchestrate and self-adapt into stronger collective intelligence without centralized control? Inspired by Friedric
arXiv:2512.23234v3 Announce Type: replace-cross Abstract: Infrared gas leak detection is important for industrial safety and environmental monitoring, but automatic detection remains challenging becau
arXiv:2606.03214v1 Announce Type: new Abstract: In this study, we evaluate the performance of skin lesion classification using ResNet-based convolutional models, focusing on the impact of demographic
arXiv:2606.03957v1 Announce Type: cross Abstract: Conversational ASR for lower-resource languages and niche domains is limited by the scarcity of domain-matched multi-speaker training data. We propose
arXiv:2606.03073v1 Announce Type: cross Abstract: Reinforcement learning (RL) for large language models (LLMs) is highly sensitive to hyperparameter configurations, making hyperparameter optimization
arXiv:2606.03566v1 Announce Type: cross Abstract: Background: The lateral ventricle choroid plexus (LVCP) is gaining recognition as a key imaging biomarker for multiple sclerosis (MS) related to physi
🇸🇻 El Salvador now has its own open persona dataset Today, working with NVIDIA and WideLabs, a Latin American leader in sovereign AI, we have Nemotron-Personas-El-Salvador. It’s the first open dataset
arXiv:2606.03893v1 Announce Type: new Abstract: Accurate execution of preoperative plans in corrective femoral osteotomies remains challenging. Current techniques are limited by variable accuracy, inv
arXiv:2606.03577v1 Announce Type: new Abstract: Wide-baseline matching (WBM) requires integrating geometric understanding, viewpoint changes, fine-grained perception, and occlusion reasoning, making i
arXiv:2606.03374v1 Announce Type: new Abstract: We present eMEM (Embodied Memory), a hybrid graph-based memory system for embodied agents operating in physical environments. Current agent memory archi
arXiv:2606.03410v1 Announce Type: new Abstract: Engineering diagrams pose a distinct challenge for vision-language models: unlike natural images or general documents, they encode information through d
Engram, a product or feature from Weaviate, has reached general availability status, meaning it is now fully released and accessible to all users. This announcement likely details the capabilities of
arXiv:2510.15780v2 Announce Type: replace-cross Abstract: Artificial intelligence (AI) is increasingly used to support renewable energy forecasting and grid operations. As renewable penetration grows,
arXiv:2606.03812v1 Announce Type: new Abstract: Operational safety in high-stakes domains such as industrial process control, autonomous, and safety-critical systems, demand reliable hazard identifica
arXiv:2506.02018v2 Announce Type: replace Abstract: Paraphrasing re-expresses meaning to enhance applications like text simplification, machine translation, and question-answering. Specific paraphrase
arXiv:2606.02629v1 Announce Type: cross Abstract: Protein-protein interactions (PPIs) are essential for many biological processes. However, existing PPI prediction approaches suffer from two major lim
arXiv:2606.02739v1 Announce Type: cross Abstract: Audio tokenizers serve as the discrete interface between continuous audio and Audio Language Models (ALMs), but existing tokenizers often struggle to
arXiv:2606.03739v1 Announce Type: new Abstract: LLM pipelines waste substantial token budgets on low-information content: repeated context, verbose responses, and redundant boilerplate. We introduce E
arXiv:2606.03937v1 Announce Type: new Abstract: While token-level entropy is commonly recognized as effective for credit assignment in text-only reinforcement learning with verifiable rewards (RLVR),
arXiv:2606.03363v1 Announce Type: new Abstract: Text-to-SQL enables natural language access to databases, and recent LLMs have substantially advanced its capabilities. Existing benchmarks such as Spid
arXiv:2606.03260v1 Announce Type: cross Abstract: Deep learning surrogates for 3D Partial Differential Equations (PDEs) often fail to generalize across geometric transformations because they depend he
arXiv:2606.02939v1 Announce Type: new Abstract: Interpretable brain-computer interface classifiers that generalize across subjects without calibration remain an open challenge. We test whether prototy
Jennifer Maas / Variety: ESA and YouGov: 212.3M people in the US between the ages of 5 and 90 play video games every week, up 3% from 2025; the average age of players rises to 37 — Two-thirds of Ameri
arXiv:2511.05050v3 Announce Type: replace-cross Abstract: In this study, a scalable online kernel learning framework is proposed for estimating bidirectional causal effects in systems characterized by
arXiv:2604.04439v2 Announce Type: replace-cross Abstract: We study how different visual information sources contribute to human decision making in dynamic visual environments. Using Atari-HEAD, a larg
arXiv:2606.02971v1 Announce Type: new Abstract: Extracting reporting obligations from EU legislation is critical for assessing and reducing regulatory reporting burden. However, distinguishing reporti
Sergiu Gatlan / BleepingComputer: Europol and international law enforcement agencies dismantle nine organized crime groups and arrest 29 in a crackdown on illegal streaming, removing 27K URLs — Europe
arXiv:2602.07842v2 Announce Type: replace Abstract: Confidence calibration is essential for making large language models (LLMs) reliable, yet existing training-free methods have been primarily studied
arXiv:2606.03331v1 Announce Type: cross Abstract: Consumer device repair is an important but underexplored testbed for large language models (LLMs). Repair tasks require reasoning over incomplete prob
arXiv:2606.02791v1 Announce Type: new Abstract: Watershed networks exhibit convergent topologies in which multiple tributaries merge into downstream channels,integrating diverse upstream hydrological
Every action that I partake is animated by two ideals: Truth and freedom. Seeing the endless attacks on both ideals throughout the West is soul-crushing. We did not lose a war of aggression. We decide
arXiv:2606.03678v1 Announce Type: new Abstract: Generating safety-critical scenarios is essential for validating and improving autonomous driving systems, yet it inherently requires maximizing adversa
arXiv:2606.03841v1 Announce Type: new Abstract: Recent progress in Large Language Model (LLM) agents has enabled promising advances in automated data science. However, existing approaches remain funda
arXiv:2606.03509v1 Announce Type: new Abstract: Building memory is essential for long-horizon planning in zero-shot embodied navigation. Detector-centric scene graphs often compress observations into
arXiv:2606.03108v1 Announce Type: new Abstract: Autonomous LLM training is often framed as recipe search, which leaves the training harness largely static. This limitation sharpens in agentic RL, wher
arXiv:2606.03003v1 Announce Type: cross Abstract: A latent world model built from an equivariant encoder E and an equivariant predictor f inherits a provable symmetry of its training loss: when the wo
Exactly right The simple fact of this case is that the police thought Henry Nowak was a racist and that meant that they did not feel obligated to extend to him any form of human decency They killed hi
This X broadcast from ComfyUI likely discusses updates or new features for integrating Claude AI code capabilities with ComfyUI, a node-based UI for AI image generation and processing workflows. The s
Learn how new Document Translation capabilities in Azure Translator, available in Foundry Tools, help developers translate images, PDFs, Office files, DITA, XLIFF, and future LLM-powered document work
arXiv:2606.03113v1 Announce Type: new Abstract: Large Language Models suffer from slow autoregressive inference. While self-speculative decoding accelerates this process, its efficiency is hampered by
arXiv:2606.03780v1 Announce Type: new Abstract: Causal tracing of factual recall has been studied predominantly in dense transformer language models, where interventions localize information flow to l
arXiv:2606.03864v1 Announce Type: cross Abstract: We introduce an explainable machine-learning approach that forecasts the structural precursors of scientific breakthroughs -- the emergence and intens
arXiv:2606.03608v1 Announce Type: cross Abstract: Test-time reinforcement learning has emerged as a promising paradigm for enhancing the complex reasoning abilities of large language models in a compl
arXiv:2606.03793v1 Announce Type: new Abstract: Multimodal Large Language Models integrate visual perception into language reasoning, introducing a continuous attack surface susceptible to adversarial
arXiv:2606.03992v1 Announce Type: new Abstract: This paper investigates 'free lunch' strategies to boost the performance of lidar semantic scene completion (SSC) without requiring complex architectura
AI has fundamentally broken the economics of cybersecurity and exposure management, compressing exploit windows from days to minutes and forcing organizations to rethink how they inventory, prioritize
arXiv:2606.03390v1 Announce Type: new Abstract: This work studies ``extreme motion generation'', which aims to maximize the Cartesian path length along a pre-defined trajectory within the manipulator'
arXiv:2606.03564v1 Announce Type: cross Abstract: Reasoning segmentation aims to segment target objects described by complex language through joint visual-textual reasoning. Existing methods typically
arXiv:2606.03694v1 Announce Type: cross Abstract: To enable meaningful human-robot interaction (HRI), a robot must continuously assess engagement by consistently tracking users over time. State-of-the
arXiv:2606.03114v1 Announce Type: new Abstract: Remote sensing change detection for real-world monitoring often relies on imperfect heterogeneous observations, where pre- and post-event images may be
arXiv:2606.02902v1 Announce Type: cross Abstract: Deep reinforcement learning (DRL) is increasingly applied to de novo molecular design, but choices in data, rewards, and evaluation can yield uneven p
arXiv:2511.11346v2 Announce Type: replace Abstract: Multi-token prediction (MTP) is a prominent strategy to significantly speed up generation in large language models (LLMs), especially in byte-level
arXiv:2606.02955v1 Announce Type: cross Abstract: Diffusion large language models promise parallel token generation, yet inference remains bottlenecked by deciding which masked tokens can be safely co