Knowledge catalogue
arXiv:2605.22664v2 Announce Type: replace Abstract: LLM agents are increasingly expected to carry out end-to-end workflows, producing complete artifacts from high-level user instructions. To meet ente
arXiv:2511.18676v2 Announce Type: replace-cross Abstract: Current vision-language models (VLMs) in medicine are primarily designed for categorical question answering (e.g., 'Is this normal or abnormal
arXiv:2606.09483v1 Announce Type: cross Abstract: Long-term memory for an LLM agent is more than retrieving the right passage at the right time. Current memory systems collapse belief revision, causal
arXiv:2601.22859v3 Announce Type: replace-cross Abstract: The evolution of Large Language Model (LLM) agents for software engineering (SWE) is constrained by the scarcity of verifiable datasets, a bot
Microsoft AI CEO Mustafa Suleyman says it's 'really, really dangerous' for Anthropic to speculate about Claude's consciousness inside its 'constitution,' or the instructions that tell the model how to
arXiv:2606.07954v1 Announce Type: cross Abstract: Training large language models (LLMs) on heterogeneous data requires selecting minibatches that balance convergence speed with coverage across domains
arXiv:2606.07706v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated strong performance across multimodal tasks, yet their safety robustness remains an open challenge. Whi
arXiv:2601.09085v2 Announce Type: replace-cross Abstract: Group Relative Policy Optimization (GRPO) has become a standard approach for training mathematical reasoning models; however, its reliance on
arXiv:2511.20397v2 Announce Type: replace Abstract: We present BLINQ, a new model-based algorithm that learns the Whittle indices of an indexable, communicating and unichain Markov Decision Process (M
arXiv:2606.07857v1 Announce Type: cross Abstract: The rise of edge-based machine learning has enabled distributed adaptation of language models across mobile and IoT devices, offering privacy preserva
arXiv:2606.07792v1 Announce Type: cross Abstract: MOLOT (Malicious Operational Logic Observation Transformer) is a static malicious-code detection system designed for SAST setup where package metadata
arXiv:2606.09002v1 Announce Type: cross Abstract: We study a stochastic multi-armed bandit problem in which the set of available arms expands over time. This setting arises in sequential experimentati
arXiv:2606.07541v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have shown strong performance on objective tasks such as video understanding and reasoning. However, it remai
mythos will be bad ON PURPOSE on ai 'frontier llm research' tasks, this is very very sad for the research community also the fact that this is un purpose not visible to the user is crazy Introducing C
NEW: Anthropic introduces Claude Fable 5, a Mythos-class model for general use. Beginning of a new class of frontier models. Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for g
arXiv:2606.08535v1 Announce Type: new Abstract: Remote sensing applications for environmental monitoring and disaster management are frequently constrained by a spatial--temporal trade-off: imagery wi
arXiv:2606.09411v1 Announce Type: cross Abstract: Large language models can be fine-tuned to encode prompt-borne secrets into fluent, seemingly benign outputs. This creates a steganographic exfiltrati
arXiv:2606.08948v1 Announce Type: cross Abstract: Comprehensive estimation of dietary micronutrients from food images could improve clinical nutrition care, but training such models requires large mul
arXiv:2606.07550v1 Announce Type: cross Abstract: Offline reinforcement learning (RL) offers a promising route for developing plasma controllers from historical tokamak data, since online trial-and-er
arXiv:2606.08572v1 Announce Type: new Abstract: While Omni-modal Large Language Models (OLLMs) have demonstrated impressive capabilities in jointly processing audio and visual streams, their ability t
arXiv:2606.08043v1 Announce Type: cross Abstract: Facial rigging - creating FACS-based blendshapes together with inner-mouth geometry (teeth, gums, and tongue) - remains a major bottleneck in 3D chara
arXiv:2606.09826v1 Announce Type: cross Abstract: Vision-language model (VLM) agents are increasingly deployed in interactive game environments. Yet game benchmarks for VLM agents typically report a s
arXiv:2606.09156v1 Announce Type: new Abstract: Autoregressive (AR) models have demonstrated strong potential in visual generation, offering superior performance with simple architectures and optimiza
arXiv:2606.07577v1 Announce Type: new Abstract: Audio-visual large language models (LLMs) hold strong promise for long-form video understanding, yet their long-video inference is fundamentally limited
arXiv:2606.08514v1 Announce Type: new Abstract: Although video virtual try-on (VVT) has achieved significant progress, existing methods still exhibit two fundamental limitations: first, they are restr
arXiv:2606.09582v1 Announce Type: new Abstract: Recent work argues for using Gaussian differential privacy (GDP) to report the privacy guarantees in privacy-preserving machine learning. We provide pri
arXiv:2606.08977v1 Announce Type: new Abstract: Motivated by the recency effect in online learning, we study algorithms for single-pass *sliding-window streaming multi-armed bandits (MABs)* in this pa
OpenAI is hosed. There is almost no reason to prefer them over Anthropic, they have lost their lead (despite every advantage in the world), they have made commitments far far beyond their means, their
arXiv:2606.08654v1 Announce Type: new Abstract: In this paper, we propose a perturbation-based conformal prediction framework for uncertainty quantification in operator learning, with a focus on the 2
arXiv:2606.08783v1 Announce Type: cross Abstract: Orthogonalized momentum updates, as used in Muon-style optimizers, have recently shown strong empirical stability in large-scale deep learning. Howeve
arXiv:2606.08938v1 Announce Type: cross Abstract: Clinical diagnosis requires flexible use of multiple reasoning paradigms under incomplete patient information. Existing LLM-based medical agents show
arXiv:2606.08638v1 Announce Type: cross Abstract: Recent research has developed practical, parallelizable first-order methods for large scale linear programming, but performance is highly dependent on
arXiv:2510.20182v2 Announce Type: replace Abstract: Pedestrian simulation traditionally relies on expert-tuned, hand-crafted models that limit scalability and generalization. Meanwhile, large-scale vi
arXiv:2606.07661v1 Announce Type: new Abstract: Parsing historical documents with complex, non-standard layouts remains a fundamental bottleneck in large-scale archival digitization. Unlike modern typ
arXiv:2606.09038v1 Announce Type: new Abstract: Large Language Models (LLMs) have enabled increasingly personalized interactions by adapting to users' preferences, contexts, and long-term histories. H
arXiv:2606.07559v1 Announce Type: cross Abstract: Fine-tuning a language model on contexts whose correct completion has a near-synonym competitor often fails silently. The cross-entropy loss decreases
arXiv:2606.07698v1 Announce Type: cross Abstract: Graph neural networks (GNNs) applied to drug-drug interaction (DDI) prediction rely exclusively on molecular structure encoded as SMILES-derived graph
arXiv:2406.05335v3 Announce Type: replace-cross Abstract: Generation of text and speech in natural languages can be modeled as a stochastic process. This idea dates back to the seminal work of Markov
arXiv:2503.05169v2 Announce Type: replace Abstract: Applying machine learning to increasingly high-dimensional problems with sparse or biased training data increases the risk that a model is used on i
arXiv:2606.08481v1 Announce Type: cross Abstract: Enterprise property graphs vary widely in schema structure, internal terminology, domain assumptions, governance constraints, and user interaction pat
arXiv:2510.17947v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are improving at an exceptional rate. With the advent of agentic workflows, multi-turn dialogue has become the de
arXiv:2603.05500v2 Announce Type: replace-cross Abstract: Efficient and stable training of large language models (LLMs) remains a core challenge in modern machine learning systems. To address this cha
arXiv:2606.07943v1 Announce Type: cross Abstract: Agent skills provide a lightweight mechanism for extending general-purpose agents, but their open format exposes them to skill-poisoning attacks. A pr
arXiv:2606.09788v1 Announce Type: new Abstract: Large-scale document processing requires contextually aware table extraction (TE) that is both accurate and efficient. Yet current approaches require bi
Google DeepMind is launching a three-month accelerator program for early-stage robotics startups across Europe, designed to support the next generation of physical AI. Selected startups receive hands-
arXiv:2606.08365v1 Announce Type: cross Abstract: Sparse autoencoder (SAE) features are increasingly used to steer language models, but feature steering is rarely clean: the same intervention can beha
arXiv:2602.15327v2 Announce Type: replace-cross Abstract: Machine learning model performance improvements tend to arise from competition and application. For deployment, we consider prescriptive scali
arXiv:2606.09189v1 Announce Type: cross Abstract: EEG foundation-model releases are usually audited one endpoint at a time: raw-reconstruction, membership inference, identity linkage, or DP-SGD on the
arXiv:2606.07532v1 Announce Type: cross Abstract: RLHF-trained models are systematically biased toward agreement over accuracy, a structural property of the training process. We present Principled Age
arXiv:2606.07974v1 Announce Type: cross Abstract: A learned world model provides a powerful physical intuition for evaluating future states. But its effectiveness in continuous control also depends cr
arXiv:2606.09740v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models demonstrate strong perfor-1 mance on language-conditioned robotic manipulation within their training dis-2 tribution
arXiv:2606.08370v1 Announce Type: cross Abstract: Standard dynamic vision sensors approximate retinal processing by detecting temporal contrast changes, offering high speed and high dynamic range. In
arXiv:2510.04127v2 Announce Type: replace-cross Abstract: Approximate nearest neighbour (ANN) search underpins large-scale retrieval, increasingly within the retrieval-augmented generation pipelines t
arXiv:2510.03389v2 Announce Type: replace-cross Abstract: Current quantum computers require algorithms that use limited resources economically. In quantum machine learning, success hinges on quantum f
I feel a lot of things changing as working software increasingly comes out on a tap. The Jevon's paradox kicks in and I feel my own demand for software growing substantially. You can ask for anything
arXiv:2410.00713v4 Announce Type: replace Abstract: Anomaly detection is a core capability for robotic perception and industrial inspection, yet most existing benchmarks are collected under controlled
Cognition AI announced the availability of Claude Fable 5 through their Devin platform, as detailed in a blog post on devin.ai. The post likely covers features, capabilities, and how to access or inte
This blog post from Google AI announces features and updates related to Gemini models, likely covering new capabilities for Gemini Live, version 3.5, and translation functionality. The announcement de
arXiv:2606.07641v1 Announce Type: new Abstract: Can vision-language models predict what a 180{eg} rotation would reveal from the original image alone? We study this ability through Rotated-Outcome Pre
arXiv:2606.08564v1 Announce Type: new Abstract: Robotic manipulation robustness often founders on the physics gap between simplified simulations and the resistance-laden real world. In this work, we e