Knowledge catalogue
arXiv:2603.11600v2 Announce Type: replace Abstract: Deep reinforcement learning for continuous control often suffers from high variance, low energy efficiency, and poor generalization under distributi
I would say that it is absurd to say that “AI belongs to the people”, when so many companies have worked so hard to develop it, but it is also absurd that Generative AI has basically been built on the
arXiv:2602.19049v2 Announce Type: replace Abstract: Large language models increasingly rely on long chains of thought to improve accuracy, yet such gains come with substantial inference-time costs. We
Gary Marcus critiques generative AI by applying the 'insanity' aphorism to highlight repetitive patterns in how these systems operate—suggesting they may be fundamentally limited by repeating the same
arXiv:2605.30965v1 Announce Type: cross Abstract: Recent advancements in text-guided audio generation have yielded promising results in diverse domains, including sound effects, speech, and music. How
This newsletter issue discusses three key topics in AI development and safety: the challenges involved in overseeing and controlling advanced AI systems, empirical findings about how protein folding A
arXiv:2603.19862v2 Announce Type: replace Abstract: Vision-Language Models like CLIP are extensively used for inter-modal tasks which involve both visual and text modalities. However, when the individ
Kiss your pensions goodbye, folks May 20 - SpaceX's (SPCX) S-1 filing Ludicrous targeted valuation: 1.8T despite 4.28B loss over last year June 11 - offering price set June 12 - first day of trading /
arXiv:2605.30651v1 Announce Type: cross Abstract: We study trajectory selection for reasoning distillation, where teacher-generated reasoning trajectories are selectively used as supervision for a stu
arXiv:2605.31486v1 Announce Type: new Abstract: We introduce and solve the novel task of controlled separation of small objects with two fingers of a multi-purpose robotic hand: after grasping into a
arXiv:2505.20795v2 Announce Type: replace Abstract: Recent robot learning methods commonly rely on imitation learning from massive robotic dataset collected with teleoperation. When facing a new task,
arXiv:2605.31343v1 Announce Type: new Abstract: Legged manipulators integrate exceptional terrain adaptability along with mobile manipulation capabilities, which make them highly promising for deploym
arXiv:2605.31376v1 Announce Type: cross Abstract: Autonomous robots in unknown indoor environments require both reliable collision avoidance and object-level understanding. Classical representations s
arXiv:2605.31259v1 Announce Type: new Abstract: Unscheduled trips of high-power pulsed converters are a leading source of downtime at large accelerator facilities. At the Spallation Neutron Source (SN
arXiv:2605.31381v1 Announce Type: new Abstract: We evaluate the consistency of automated judges in conducting a multi-dimensional safety evaluation in a reference-free setup. Our results indicate that
arXiv:2605.31057v1 Announce Type: new Abstract: Dense self-attention is the compute and quality bottleneck of long-video diffusion inference: cost grows quadratically with the sequence length, and bey
arXiv:2605.30365v1 Announce Type: cross Abstract: Retrieval-augmented text-to-music (TTM) systems augment underspecified user prompts using captions retrieved from a music caption dataset. This design
arXiv:2605.30904v1 Announce Type: new Abstract: Most visual tokenizers for image generation are bifurcated into two families with complementary limitations: continuous VAEs offer high-fidelity reconst
The example of a growing restaurant Imagine you are running a restaurant chain. You just can't physically feel and touch things to know how your business operates. You need tools and a digital replica
arXiv:2602.01011v4 Announce Type: replace-cross Abstract: Multi-agent LLM systems are increasingly deployed as autonomous collaborators, where agents interact freely rather than execute fixed, pre-spe
arXiv:2605.30717v1 Announce Type: new Abstract: Language models (LMs) can produce gendered language and stereotypes even when given neutral prompts. Most prior work on gender bias in LMs primarily exa
Neurosymbolic rising! I've wanted to work on deep neurosymbolic integration for a while: if you make an 800k transformer reason *like* a logical solver, you get 100% on sudoku-extreme w. 15m of train
arXiv:2605.30519v1 Announce Type: new Abstract: Autoregressive (AR) video generation extends videos by producing latent chunks sequentially, but scaling to long videos requires repeated access to a gr
arXiv:2501.12020v2 Announce Type: replace Abstract: Face recognition systems (FRS) exhibit significant accuracy differences based on the user's gender. Since such a gender gap reduces the trustworthin
arXiv:2602.18333v2 Announce Type: replace-cross Abstract: Despite the remarkable practical success of transformer-based language models, recent work has raised concerns about their ability to perform
arXiv:2605.31518v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) decompose neural network activations into interpretable features, but many learned features never activate, a problem called
arXiv:2512.14366v2 Announce Type: replace Abstract: Implicit Neural Representations (INRs) based on vanilla Multi-Layer Perceptrons (MLPs) are widely believed to be incapable of representing high-freq
arXiv:2506.12060v2 Announce Type: replace-cross Abstract: Cybersecurity organizations are adapting to GenAI integration through modified frameworks and hybrid operational processes, with success influ
OpenAI outlines its positions on AI policy priorities and explains its approach to political engagement and advocacy efforts. The document likely covers key regulatory areas OpenAI supports, such as s
arXiv:2510.10544v3 Announce Type: replace-cross Abstract: We derive a novel PAC-Bayesian generalization bound for reinforcement learning that explicitly accounts for Markov dependencies in the data, t
arXiv:2605.30991v1 Announce Type: cross Abstract: Inference-time reward alignment steers pretrained diffusion and flow-based generative models to satisfy user-specified rewards without retraining. Rec
arXiv:2601.11702v3 Announce Type: replace-cross Abstract: AI compliance is becoming increasingly critical as AI systems grow more powerful and pervasive. Yet the rapid expansion of AI policies creates
arXiv:2602.15778v2 Announce Type: replace Abstract: Evaluating the quality of automatically generated text often relies on LLM-as-a-judge (LLM-judge) methods. While effective, these approaches are com
arXiv:2508.02217v2 Announce Type: replace Abstract: Multi-objective reinforcement learning (MORL) is a fundamental framework for real-world decision-making problems involving multiple conflicting crit
arXiv:2511.17185v2 Announce Type: replace Abstract: We propose PostCam, a streamlined framework for novel-view video generation that achieves superior detail preservation and precise camera trajectory
Prediction: Nobody knows when this will all collapse, but 2026 will be remembered in hindsight as the year in which retail investors and index funds were left holding the bag. It's funny how people th
arXiv:2605.31545v1 Announce Type: new Abstract: As Large Language Models (LLMs) evolve from general-purpose assistants to user-centric agents, personalization has become central to aligning model beha
arXiv:2605.30803v1 Announce Type: new Abstract: LLM judges are increasingly used to evaluate open-ended responses, but their scores depend strongly on the rubrics that condition them. A vague rubric a
arXiv:2605.30695v1 Announce Type: new Abstract: Deploying vision-language-action (VLA) policies in industrial environments requires the ability to teach new tasks at low cost, a property current VLAs
arXiv:2605.30632v1 Announce Type: cross Abstract: We introduce Rationalize, a role-pair framework for shared semantic reasoning between humans and AI models in data-driven sensemaking. Building on ide
arXiv:2605.30957v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have emerged as a promising paradigm for general-purpose robot control. However, their performance remains fundament
arXiv:2605.30966v1 Announce Type: cross Abstract: Knowledge graphs over corpora of inter-referencing documents - scholarly papers, legal opinions, policy briefs - encode the topology of reference but
arXiv:2603.17145v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed as automated evaluators that assign numeric scores to model outputs, a paradigm known a
arXiv:2504.11972v3 Announce Type: replace Abstract: Extractive QA tasks are commonly evaluated using Exact Match (EM) and F1-score, but these metrics often fail to reflect true model performance. Rece
arXiv:2510.11711v2 Announce Type: replace Abstract: This paper proposes a synergy of amortised and particle-based methods for sampling from distributions defined by unnormalised density functions. We
arXiv:2605.31328v1 Announce Type: new Abstract: Emergent misalignment (EM) is the surprising tendency of language models to become broadly misaligned after fine-tuning on narrowly misaligned examples.
arXiv:2605.30368v1 Announce Type: cross Abstract: Surrogate Safety Measures (SSMs) are extensively utilised in the evaluation of traffic risk in automated driving contexts. However, the majority of SS
arXiv:2605.30524v1 Announce Type: new Abstract: Large language models are now adapted through chains of post-training stages rather than through a single instruction-tuning pass. This paper studies wh
arXiv:2601.01456v2 Announce Type: replace-cross Abstract: In this paper, we revisit multimodal few-shot 3D point cloud semantic segmentation (FS-PCS), identifying a conflict in 'Fuse-then-Refine' para
// Reusable Context Engineering // Context bloat quietly kills long-horizon runs, but you can fix it from the outside without fine-tuning the underlying agent. (bookmark this) Context management is us
arXiv:2605.30960v1 Announce Type: new Abstract: Accurate Zeroth-Order (ZO) Hessian estimation is a cornerstone of derivative-free methods, essential for tasks such as bilevel optimization, Bayesian in
arXiv:2605.31043v1 Announce Type: cross Abstract: Cross-domain EEG decoding remains challenging despite advances in Riemannian deep learning: covariance matrices from different subjects occupy systema
arXiv:2412.03876v2 Announce Type: replace Abstract: Text-to-Image (T2I) diffusion models are widely recognized for their ability to generate high-quality and diverse images based on text prompts. Howe
arXiv:2605.30461v1 Announce Type: cross Abstract: We present a distributed approach for constrained Multi-Agent Reinforcement Learning (MARL) that combines state-augmented policy learning with distrib
arXiv:2511.03100v2 Announce Type: replace-cross Abstract: The agent-environment co-design paradigm jointly optimises agent policies and environment configurations in search of improved system performa
arXiv:2602.13110v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used as scalable judges in pairwise evaluation, but they remain prone to miscalibration and bias
arXiv:2605.31014v1 Announce Type: new Abstract: Multi-omics data provide complementary molecular characterizations of disease phenotypes and play an important role in disease diagnosis and subtype cla
In this post, we use a lakehouse data agent to demonstrate how you can use Policy for deterministic access control and Lambda interceptors for dynamic validation. We then show how to combine Lambda in
arXiv:2605.30698v1 Announce Type: cross Abstract: Vision-language models (VLMs) have achieved strong performance on visual question answering (VQA). To mitigate individual hallucinations and blind spo
arXiv:2605.30608v1 Announce Type: new Abstract: Learning a shared representation between spoken text and gesture is central to co-speech gesture retrieval, synthesis, and understanding, but remains ch