Knowledge catalogue
New paper: research agenda for secret loyalties Imagine a frontier model that has been trained to covertly advance a specific actor's interests (a nation-state, a CEO, an adversary). @joemkwon argues
arXiv:2605.11102v1 Announce Type: new Abstract: Neural warm starts can sharply reduce the number of Newton-Raphson iterations required to solve the AC power flow problem, but existing supervised appro
arXiv:2605.11583v1 Announce Type: cross Abstract: Modern low-field magnetic resonance imaging (MRI) technology offers a compelling alternative to standard high-field MRI, with portable, low-cost syste
Gary Marcus argues that current large language models (LLMs) do not constitute artificial general intelligence (AGI), though they will cause some job displacement. He suggests that true AGI, if achiev
arXiv:2605.12233v1 Announce Type: new Abstract: Terminal agents are increasingly capable of executing complex, long-horizon tasks autonomously from a single user prompt. To do so, they must interpret
no remorse, just further evasion. so slick; so dangerous. 🚨 SEVEN OPENAI INSIDERS HAVE ACCUSED SAM ALTMAN OF LYING Today on cross, Musk's lawyer walked Altman through all of them: >Ilya Sutskever (co-
arXiv:2605.11970v1 Announce Type: new Abstract: Most dimensionality reduction methods treat data as discrete point clouds, ignoring the continuous domain structure inherent to many real-world processe
arXiv:2605.12207v1 Announce Type: cross Abstract: We study the extit{parameter placement problem}: given a fixed budget of k trainable entries within the B matrix of a LoRA adapter (A frozen), does th
Not to mention 7 blog posts dropped today, including a new Deep Agents version with significant improvements… Especially excited about the Code Interpreter feature which is a sneaky powerful feature e
arXiv:2603.27358v2 Announce Type: replace Abstract: Despite a long tradition of work on extractive summarization, which by nature aims to recover the most important propositions in a text, little work
Reinforcement-learning agents — AI systems that learn by trial and error — can convert computation into new knowledge. That’s the focus of a new engineering-level collaboration between NVIDIA and Inef
NVIDIA Nemotron models received native support integration in Deep Agents version 0.6, enabling improved language model capabilities within the LangChain framework. This update allows developers to le
Observability going from 'read the traces' to 'the traces read themselves and tell you what to fix.' That's the feedback loop most agent teams are missing. 🚀Launching: LangSmith Engine LangSmith Engin
Sam Tabahriti / Reuters: Ofcom fines an unnamed suicide forum £950K, the largest OSA fine so far, for hosting illegal content accessible in the UK; the forum is linked to 130+ deaths — Britain's commu
arXiv:2603.18702v3 Announce Type: replace Abstract: We study off-policy learning (OPL) in contextual bandits, which plays a key role in a wide range of real-world applications such as recommendation s
Off to an amazing start at @LangChain Interrupt 🪁🦜 Including: 📣 Shoutout from @hwchase17 during the opening keynote! 🪁 CopilotKit booth with the best staff, demos and merch 🍸 Agents After Dark Happy H
arXiv:2505.17506v2 Announce Type: replace-cross Abstract: We study offline constrained reinforcement learning with general function approximation in discounted constrained Markov decision processes. P
arXiv:2605.11479v1 Announce Type: new Abstract: Policy evaluation is a fundamental component of the development and deployment pipeline for robotic policies. In modern manipulation systems, this probl
arXiv:2605.12400v1 Announce Type: new Abstract: We study {on-policy self-distillation} (OPSD), where a language model improves its reasoning ability by distilling privileged teacher distributions alon
arXiv:2605.12038v1 Announce Type: new Abstract: Cross-embodiment video generation aims to transfer motions across different humanoid embodiments, such as human-to-robot and robot-to-robot, enabling sc
arXiv:2605.12480v1 Announce Type: new Abstract: Recent advances in joint audio-video generation have been remarkable, yet real-world applications demand strong per-modality fidelity, cross-modal align
arXiv:2605.11629v1 Announce Type: new Abstract: Recent multimodal large language models (MLLMs) have shown strong chain-of-thought (CoT) reasoning ability on vision-language tasks, but their direct de
Elon Musk posted on X about traveling to Beijing aboard Air Force One, indicating a trip to China's capital. The post suggests either an official government delegation or a significant business visit
arXiv:2605.11978v1 Announce Type: new Abstract: The performance of Large Language Models (LLMs) on downstream tasks is fundamentally constrained by the capabilities acquired during pre-training. Howev
arXiv:2605.11051v1 Announce Type: cross Abstract: LLM-based Software Engineering agents face a critical bottleneck: context length limitations cause failures on complex, long-horizon tasks. One promis
arXiv:2605.11471v1 Announce Type: new Abstract: Matrix product operator Born machines (MPO-BMs) are tractable tensor-network models for probabilistic modeling, but their efficient approximation capabi
arXiv:2605.12206v1 Announce Type: new Abstract: In reinforcement learning (RL), agents acting in partially observable Markov decision processes (POMDPs) must rely on memory, typically encoded in a rec
arXiv:2605.12168v1 Announce Type: new Abstract: Artificial intelligence systems typically rely on large, centrally collected datasets, a premise that does not hold in many real-world domains such as h
One of the biggest challenges with agents is that they produce way more than just tokens. Tool calls. State updates. Intermediate reasoning. Subagent progress. File changes. Custom events. Structured
arXiv:2605.11755v1 Announce Type: cross Abstract: Diffusion models and flow-based methods have shown impressive generative capability, especially for images, but their sampling is expensive because it
arXiv:2605.05630v2 Announce Type: replace Abstract: Hidden malicious intent in multi-turn dialogue poses a growing threat to deployed large language models (LLMs). Rather than exposing a harmful objec
arXiv:2605.11742v1 Announce Type: new Abstract: Online Continual Learning (OCL) aims to learn from endless nonext{-}stationary data streams, yet most existing methods assume a flat label space and ove
arXiv:2605.12340v1 Announce Type: cross Abstract: Learning-to-Defer (L2D) methods route each query either to a predictive model or to external experts. While existing work studies this problem in batc
Open Source always wins 👀 Save your credits and use open source models when you can. The new LTX 2.3 lipdub LoRA paired with Chatterbox TTS voice cloning model is the best workflow for lip syncing, ch
OpenAI Global Affairs: OpenAI endorses the Kids Online Safety Act and Illinois SB 315, an AI safety bill to create requirements around transparency, incident reporting, and more — Welcome (back) to Th
Maggie Eastland / Bloomberg: OpenAI says it would support a global AI governance body that is led by the US and includes China as a member, similar to the International Atomic Energy Agency — OpenAI w
Jared Perlo / NBC News: OpenEvidence, an AI-powered medical search tool, says it's used by two-thirds of US physicians, or ~650K doctors, and an additional 1.2M doctors internationally — OpenEvidence,
arXiv:2605.11199v1 Announce Type: cross Abstract: Trained lattice samplers are usually judged by the ensembles they generate. Here we instead analyze the trained field-space function itself: a flow-ma
arXiv:2605.12235v1 Announce Type: cross Abstract: We study optimal policy learning under combined budget and minimum coverage constraints. We show that the problem admits a knapsack-type structure and
arXiv:2605.11291v1 Announce Type: new Abstract: In this paper, we provide a computable characterization of the geometry of optimal representations in Contrastive Learning (CL) when the classes are imb
arXiv:2605.11172v1 Announce Type: new Abstract: We introduce SODA, a generalization of Optimistic Dual Averaging, which provides a common perspective on state-of-the-art optimizers like Muon, Lion, Ad
arXiv:2605.11977v1 Announce Type: new Abstract: We present a unified framework for 3D geometric abstraction using a single continuous 4D wire, parameterized as a B-spline with spatial coordinates and
arXiv:2605.12419v1 Announce Type: new Abstract: Despite the rapid advancements in large language model (LLM) development, fine-tuning them for specific tasks often results in the catastrophic forgetti
arXiv:2605.12446v1 Announce Type: cross Abstract: Large language models (LLMs) often produce answers with high certainty even when they are incorrect, making reliable confidence estimation essential f
arXiv:2602.12139v2 Announce Type: replace Abstract: Transformers excel at time series modelling through attention mechanisms that capture long-term temporal patterns. However, they assume uniform time
arXiv:2605.11803v1 Announce Type: new Abstract: As Video Large Language Models (Video-LLMs) scale to longer and more complex videos, their inference cost grows rapidly due to the large volume of visua
arXiv:2605.11570v1 Announce Type: new Abstract: Activation functions are what make deep networks expressive: without them, the model collapses to a linear map. Yet we still evaluate training mostly fr
At the Android Show yesterday, we introduced Googlebooks: a new category of premium laptops built with Gemini’s helpfulness at the core. Designed for Gemini Intelligence, Googlebooks will give persona
Our evaluations show that frontier AI's cyber capabilities are advancing quickly. The length of cyber tasks frontier models can complete has been doubling every few months, and this rate has become fa
OpenAI details its response to the TanStack “Mini Shai-Hulud” supply chain attack, outlines protections taken to secure systems and signing certificates, and explains why macOS users must update OpenA
arXiv:2605.12345v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) techniques offer task-specific fine-tuning at a fraction of the cost of full fine-tuning, but require separate fi
arXiv:2605.11459v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models achieve remarkable flexibility and generalization beyond classical control paradigms. However, most prevailing VLA
arXiv:2605.11525v1 Announce Type: new Abstract: Missing values are routinely treated as defects to be eliminated through deletion or imputation prior to machine learning. In many applied domains, howe
arXiv:2506.23619v2 Announce Type: replace-cross Abstract: This paper investigates the impact of posterior drift on out-of-sample forecasting accuracy in overparametrized machine learning models. We do
arXiv:2605.11178v1 Announce Type: new Abstract: Neural Sheaf Diffusion (NSD) generalizes diffusion-based Graph Neural Networks by replacing scalar graph Laplacians with sheaf Laplacians whose learned
arXiv:2605.12199v1 Announce Type: new Abstract: Emergent misalignment (EM), where fine-tuning on a narrow task (like insecure code) causes broad misalignment across unrelated domains, was first demons
arXiv:2605.12313v1 Announce Type: new Abstract: Multi-hop question answering (QA) remains a significant challenge in the biomedical domain, requiring systems to integrate information across multiple s
A peer-to-peer AI inference mesh is a decentralized network architecture where agents connect directly to discover peers and communicate through distributed protocols to share inference workloads . Su
Harrison Chase delivered a keynote address at a LangChain event that drew a large audience, as indicated by the 'packed house' reference. The event appears to have been interrupted at some point durin
arXiv:2605.12072v1 Announce Type: new Abstract: Dropout-based sparse-view 3D Gaussian Splatting (3DGS) methods alleviate overfitting by randomly suppressing Gaussian primitives during training. Existi