Knowledge catalogue
Tim Bradshaw / Financial Times: Despite the “DeepMind mafia” pulling billions into London AI startups, none of Demis Hassabis' former lieutenants is building a homegrown UK frontier AI model — The tec
arXiv:2606.26155v1 Announce Type: new Abstract: Interpreting and controlling model behaviors through activation steering methods requires many pairs of contrastive samples that clearly exhibit desired
arXiv:2606.26397v1 Announce Type: cross Abstract: Real-world decision-making often requires balancing multiple conflicting objectives, a challenge that standard Reinforcement Learning (RL) frequently
arXiv:2606.26918v1 Announce Type: new Abstract: Large language models can serve as capable long-horizon agents, but their out-of-distribution (OOD) generalization remains weak. We identify a key sourc
arXiv:2606.26602v1 Announce Type: new Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated impressive fine-grained perception capabilities. However, existing ben
arXiv:2601.01701v2 Announce Type: replace-cross Abstract: Anomaly detection is increasingly becoming crucial for maintaining the safety, reliability, and efficiency of industrial systems. Recently, wi
arXiv:2606.26398v1 Announce Type: new Abstract: High-precision remote perception is often hindered by the severe bandwidth constraints of Vehicle-to-Everything (V2X) networks. We propose extit{DinoLin
arXiv:2606.26668v1 Announce Type: cross Abstract: Video customization based on Text-to-Video (T2V) models aims to learn specific features from reference data to generate controllable videos. While sig
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:2606.26116v1 Announce Type: cross Abstract: A brand whose customers use both ChatGPT and Claude for product recommendations faces a strategic choice: a single optimization playbook, or one per p
arXiv:2508.02753v5 Announce Type: replace-cross Abstract: Time Series Forecasting (TSF) faces persistent challenges in modeling intricate temporal dependencies across different scales. Despite recent
arXiv:2606.27153v1 Announce Type: cross Abstract: Matrix-orthogonalization-based optimizers, exemplified by Muon, have demonstrated strong convergence behavior across a wide range of modern deep learn
arXiv:2606.27372v1 Announce Type: new Abstract: The softmax activation in multihead attention (MHA) is the de facto standard for attention-based models in visual perception tasks. However, standard so
arXiv:2606.26738v1 Announce Type: new Abstract: While recent advancements in generative image editing models have achieved stunning visual fidelity, it remains an open question whether these systems p
arXiv:2606.26686v1 Announce Type: new Abstract: In order to screen a prompt or a response, the recent guardrail methods generate a chain-of-thought (CoT) before they issue a verdict. This design follo
arXiv:2606.26122v1 Announce Type: new Abstract: Recent methods train search agents via reinforcement learning from (question, answer, evidence) tuples without requiring expert trajectories. The tuples
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:2606.26361v1 Announce Type: new Abstract: ML foundation models are able to emulate atmospheric dynamics accurately and efficiently but operate as opaque ``black boxes''. We investigate the inter
arXiv:2606.27371v1 Announce Type: new Abstract: State-of-the-art flow models generate stunning images from text or image prompts. However, they suffer from diversity collapse when generating multiple
arXiv:2606.26121v1 Announce Type: cross Abstract: Global insect population declines necessitate scalable, continuous monitoring systems, yet existing vision-based solutions remain constrained by high
arXiv:2606.26114v1 Announce Type: cross Abstract: We examine the structural transformation of creative industries under generative artificial intelligence, drawing on 374 primary sources spanning poli
arXiv:2606.26707v1 Announce Type: cross Abstract: Adversarial APKs are Android applications modified in the problem space to evade machine-learning malware detectors. In this work, we first show that,
arXiv:2606.26716v1 Announce Type: cross Abstract: Arbitrary slice super-resolution reconstructs isotropic volumes from anisotropic clinical acquisitions by synthesizing intermediate slices at arbitrar
arXiv:2601.16632v4 Announce Type: replace-cross Abstract: Time series forecasting has witnessed significant progress with deep learning. While prevailing approaches enhance forecasting performance by
arXiv:2606.26429v1 Announce Type: cross Abstract: Current LLM evaluation relies on two complementary but often disconnected signals: static benchmarks with objective correctness labels and arena-style
arXiv:2606.26120v1 Announce Type: new Abstract: Diffusion Large Language Models (dLLMs) offer a promising alternative to autoregressive models, excelling in text generation tasks due to their bidirect
Dynamic workflows (generating harnesses on the fly) are a new form of test-time compute. But LLMs aren't great at building them. I often have to steer agents to generate complex patterns. Curious how
arXiv:2606.16203v3 Announce Type: replace Abstract: Post-traumatic epilepsy (PTE) is a severe complication of traumatic brain injury (TBI). Yet, early identification remains challenging due to the com
arXiv:2606.27268v1 Announce Type: cross Abstract: Recently, a few works have made early attempts to study test-time scaling for embodied tasks. However, two major challenges remain unsolved: (1) reaso
arXiv:2606.27246v1 Announce Type: new Abstract: We study a solvable high-dimensional model of generative adversarial network (GAN) training in which a linear generator learns a low-dimensional subspac
arXiv:2606.27119v1 Announce Type: cross Abstract: Foundation decoders, a class of high-capacity neural decoders, are leading candidates for fault-tolerant quantum computing, with accurate and efficien
arXiv:2510.05531v2 Announce Type: replace-cross Abstract: Bosonic Gaussian unitaries are fundamental building blocks of central continuous-variable quantum technologies such as quantum-optic interfero
arXiv:2606.26758v1 Announce Type: new Abstract: High-performance GPU kernels are critical for reducing the exponentially growing computational costs of large language models (LLMs), but their developm
arXiv:2606.26969v1 Announce Type: new Abstract: Does intelligence require the ability to reason about phenomena beyond direct experience? It is natural to suspect that some complex thought cannot be c
arXiv:2606.26337v1 Announce Type: new Abstract: Gradient Boosted Decision Trees (GBDT), exemplified by LightGBM, spend a dominant fraction of training time -- typically 65-70% -- constructing per-feat
arXiv:2604.01193v2 Announce Type: replace Abstract: Can a large language model (LLM) improve at code generation using only its own raw outputs, without a verifier, a teacher model, or reinforcement le
arXiv:2606.26432v1 Announce Type: new Abstract: Tabular foundation models achieve strong accuracy on choice prediction tasks, but their predictions often violate the economic logic those tasks require
arXiv:2606.26590v1 Announce Type: new Abstract: Security misconfigurations in Terraform Infrastructure-as-Code are a growing risk in cloud deployments, and large language models are increasingly used
arXiv:2606.27330v1 Announce Type: cross Abstract: Multimodal web agents can assist humans in operating repetitive GUI tasks, where effective task planning is essential for decomposing complex tasks in
arXiv:2606.26991v1 Announce Type: cross Abstract: X-ray computed tomography reconstruction is an ill-posed inverse problem, particularly in low-dose and sparse-angle settings where measurements are no
arXiv:2508.17916v2 Announce Type: replace Abstract: Depth estimation is a foundational component for 3D reconstruction in minimally invasive endoscopic surgeries. However, existing monocular depth est
arXiv:2606.27277v1 Announce Type: new Abstract: Earth Observation (EO) forecasting aims to predict future Earth surface dynamics from satellite observations under changing meteorological conditions. I
arXiv:2606.26472v1 Announce Type: cross Abstract: As reasoning models emit chains of thought tens of thousands of tokens long, KV cache increasingly becomes a deployment bottleneck. Existing cache evi
arXiv:2606.26273v1 Announce Type: new Abstract: Symmetries are important for many deep learning tasks, ranging from applications in the sciences to medical imaging. However, there is an ongoing debate
arXiv:2606.26560v1 Announce Type: new Abstract: Delta-rule linear attention improves recurrent memory updates by correcting what is already stored at the current write address before writing new conte
arXiv:2606.27354v1 Announce Type: cross Abstract: Neural surrogate models offer fast approximate mappings from PDE parameters to solutions, but they typically treat solving as a purely statistical tas
arXiv:2606.26772v1 Announce Type: new Abstract: Differentially private (DP) training of neural networks is often hindered by the large amount of noise required by gradient-based methods such as DP-SGD
arXiv:2510.17459v3 Announce Type: replace-cross Abstract: In this work, we propose a flow-matching Markov chain Monte Carlo (FM-MCMC) algorithm for estimating the orbital parameters of exoplanetary sy
arXiv:2606.26422v1 Announce Type: new Abstract: Researchers increasingly use text classification--supervised models or large language models--to measure constructs from natural language, providing met
arXiv:2606.26775v1 Announce Type: new Abstract: Multimedia event extraction aims to jointly identify events and their arguments across multiple modalities, such as text and images, to support more com
arXiv:2606.26492v1 Announce Type: cross Abstract: Deep Learning (DL) programs can fail during training for many reasons, and diagnosing the cause is a costly and time-consuming maintenance task. Techn
arXiv:2606.26994v1 Announce Type: cross Abstract: Existing referring video segmentation methods often treat a video as a single event consisting of multiple images, overlooking the fact that a video t
arXiv:2606.26780v1 Announce Type: new Abstract: Spin plays a crucial role in many ball sports due to its effect on the trajectory of the ball. Vision-based estimation of the ball's spin during a game
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:2606.26327v1 Announce Type: cross Abstract: In actor-critic reinforcement learning, network architectures are typically manually designed. Automating this design is challenging because each cand
arXiv:2606.26578v1 Announce Type: new Abstract: Automating optimization modeling from natural language with large language models (LLMs) faces two key challenges. First, training corpora lack structur
arXiv:2606.27280v1 Announce Type: new Abstract: We present a patch descriptor retrieval method that returns the exact nearest neighbour -- provably identical to exhaustive full-vector search -- while
excited to come down to SF for @aidotengineer next week! let’s hang :) We're hosting a BabyAGI x Physical AI Happy Hour with @yoheinakajima on June 30th, 6PM in SF! If you're building across AI agents
Excited to see @cohere open-source how they use AI coding agents to maintain their vLLM fork. 🙌 Keeping a long-lived fork in sync is tricky. Their agent treats it as a control loop: rebase onto each u
arXiv:2606.26561v1 Announce Type: new Abstract: Hepatitis C is a liver infection caused by a virus, which results in mild to severe inflammation of the liver. Over many years, hepatitis C gradually da