Knowledge catalogue
arXiv:2605.00942v1 Announce Type: cross Abstract: Developing effective test cases capable of thoroughly exercising large-scale software systems is inherently difficult, especially if such systems have
arXiv:2605.01640v1 Announce Type: cross Abstract: Training compute is increasingly outpacing the availability of high-quality data. This shifts the central challenge from optimal compute allocation to
arXiv:2602.11543v2 Announce Type: replace Abstract: Pretraining large language models (LLMs) typically requires centralized clusters with thousands of high-memory GPUs (e.g., H100/A100). Recent decent
arXiv:2605.01625v1 Announce Type: new Abstract: Proteins are inherently multiscale physical systems whose functional properties emerge from coordinated structural organization across multiple spatial
arXiv:2605.01699v1 Announce Type: new Abstract: Recent attacks show that behavioural unlearning of large language models leaves internal traces recoverable by adversarial probes. We characterise where
arXiv:2605.02144v1 Announce Type: new Abstract: Self-attention in Transformers is typically implemented as softmax(QK^op/sqrt{d})V, where Q=XW_Q, K=XW_K, and V=XW_V are learned linear projections of t
arXiv:2605.01630v1 Announce Type: new Abstract: Rankings produced by holistic LLM-as-a-judge scoring are sensitive to the bias of the chosen judge model. We show that switching to binary rubric scorin
Proud of my analyst, Hermes This is what he has achieved after 1.5+ months of internship with me - Got me off X (doomscrolling cut from 2 hrs → 30 mins) - Practically paid for his salary via PMs b
arXiv:2605.01017v1 Announce Type: new Abstract: We introduce Xiaohongshu Social Comparison Reader Elicitation (XHS-SCoRE), a reader-grounded benchmark for detecting if a text-only Xiaohongshu (RedNote
The agentic era is here, and the public sector is at the forefront of leading this transformation.At Google Cloud Next ’26, it was clear that academia and public sector organizations are no longer jus
arXiv:2605.01467v1 Announce Type: cross Abstract: Tensor completion has emerged as a powerful framework for recovering missing data in multidimensional signals by exploiting low-rank tensor structures
arXiv:2605.01502v1 Announce Type: new Abstract: Epistemic uncertainty estimation is essential for identifying regions where deep learning system outputs may be unreliable. However, existing approaches
arXiv:2605.02184v1 Announce Type: new Abstract: Pansharpening aims to generate high-resolution multispectral (HRMS) images by fusing low-resolution multispectral (LRMS) and high-resolution panchromati
arXiv:2605.02003v1 Announce Type: new Abstract: Machine Learning (ML) has transformed many scientific fields, yet key applications still lack standardized benchmarks. Raman spectroscopy, a widely used
arXiv:2605.01991v1 Announce Type: cross Abstract: Learning, prediction, and compression are intimately connected: a model that accurately predicts the next symbol in a sequence can be coupled with a s
arXiv:2605.02552v1 Announce Type: new Abstract: Chemotherapy dose optimization can be formulated as a dynamic treatment regime, requiring sequential decisions under uncertainty that must balance tumor
arXiv:2605.02469v1 Announce Type: new Abstract: Online reinforcement learning with verifiable rewards (RLVR) turns checkable outcomes into a scalable training signal, but it keeps rollout generation,
arXiv:2605.01913v1 Announce Type: cross Abstract: Fine-tuning safety-aligned language models for downstream tasks often leads to substantial degradation of refusal behavior, making models vulnerable t
arXiv:2605.02801v1 Announce Type: new Abstract: As large language model (LLM) agents evolve from isolated tool users into coordinated teams, reinforcement learning (RL) must optimize not only individu
arXiv:2605.01403v1 Announce Type: new Abstract: Multi-label node classification (MLNC) has recently been addressed by increasingly complex label-aware designs that explicitly model node-label interact
arXiv:2605.02623v1 Announce Type: new Abstract: Video Moment Retrieval (VMR) aims to localize temporal segments in videos that correspond to a natural language query, but typically assumes only a sing
arXiv:2605.01831v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback has become the standard paradigm for language model alignment, where reward models directly determine alignme
arXiv:2605.02370v1 Announce Type: new Abstract: This paper presents a novel model predictive control (MPC) approach for autonomous pick-and-place between moving platforms with a hook-equipped aerial m
arXiv:2605.01339v1 Announce Type: new Abstract: Learning-based approaches to verifying unknown Markov decision processes (MDPs) often employ uncertain MDPs. These models use, for example, confidence i
arXiv:2605.00966v1 Announce Type: new Abstract: Hierarchical Gaussian Filtering (HGF) networks allow for efficient updating of posterior distributions (beliefs) about hidden states of an agent's envir
arXiv:2605.00916v1 Announce Type: new Abstract: Reliable segmentation of multiphase pore-scale X-ray images of rocks is necessary to quantify fluid saturation, connectivity, and interfacial geometry.
arXiv:2605.01429v1 Announce Type: cross Abstract: Libraries of Low-Rank Adaptation (LoRA) adapters are becoming a practical by-product of parameter-efficient adaptation. Once such adapters accumulate,
arXiv:2510.13768v2 Announce Type: replace Abstract: We study the problem of training self-supervised foundation models for functional MRI. Our main contributions are: (1) we introduce a new model fami
arXiv:2605.01489v1 Announce Type: cross Abstract: Frontier scientific reasoning is rapidly emerging as a key foundation for advancing AI agents in automated scientific discovery. Deep research agents
See you all soon! We've got some fun announcements ahead. I'll also be doing a workshop on 'how we Claude Code' with some workflows I'm excited to share. Don't worry if you're not there, everything wi
arXiv:2605.02757v1 Announce Type: new Abstract: Vision-language-action (VLA) models typically rely on large-scale real-world videos, whereas simulated data, despite being inexpensive and highly parall
arXiv:2603.27259v2 Announce Type: replace Abstract: Long video understanding (LVU) remains a core challenge in multimodal learning. Although recent vision-language models (VLMs) have made notable prog
arXiv:2605.01327v1 Announce Type: cross Abstract: Existing reinforcement learning approaches for Large Language Models typically perform policy optimization at the granularity of individual tokens or
arXiv:2605.01823v1 Announce Type: new Abstract: Recently, Reinforcement Learning from Verifiable Rewards (RLVR) has been established as a highly effective technique for augmenting the math reasoning s
arXiv:2303.10971v2 Announce Type: replace Abstract: The matching of 3D shapes has been extensively studied for shapes represented as surface meshes, as well as for shapes represented as point clouds.
arXiv:2605.02601v1 Announce Type: new Abstract: We present our shared task on evaluating the adaptability of LLMs and NLP systems across multiple languages and cultures. The task data consist of an ex
arXiv:2605.01191v1 Announce Type: new Abstract: Vision-language-action (VLA) models have advanced the field of embodied manipulation by harnessing broad world knowledge and strong generalization. Howe
arXiv:2605.01496v1 Announce Type: new Abstract: This report presents the results and findings of the first edition of the Short-Films 20K (SF20K) Competition, held in conjunction with the SLoMO Worksh
arXiv:2605.02475v1 Announce Type: cross Abstract: Stories hold a reader's attention because they have causes, secrets, and consequences. Shadow-Loom is an experimental open-source framework that turns
arXiv:2605.02105v1 Announce Type: cross Abstract: Pretraining optimizers are tuned to produce the strongest possible base model, on the assumption that a stronger starting point yields a stronger mode
arXiv:2605.00519v2 Announce Type: cross Abstract: The operational landscape of local Large Language Model (LLM) inference has shifted from lightweight models to datacenter-class weights exceeding 70B
arXiv:2605.00382v2 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly deployed to generate code for human-centered applications where demographic fairness is critical. Howeve
Some things never change. If you don’t understand this one, you don’t understand what’s happening AI. Marcus, 1998: neural nets have trouble generalizing far beyond the data. Marcus, 2001, 2012, 2019,
arXiv:2605.00835v1 Announce Type: new Abstract: Choosing between classical and Bayesian sparse regression methods involves a real trade-off: penalized estimators like Lasso run in milliseconds but giv
arXiv:2605.02152v1 Announce Type: new Abstract: Diffusion-based image editing offers strong semantic controllability, but remains computationally expensive due to iterative high-resolution denoising o
arXiv:2605.02684v1 Announce Type: new Abstract: Spectral-based machine learning models have been increasingly deployed in chemometrics and spectroscopy, where predictive accuracy is as important as ex
arXiv:2605.01466v1 Announce Type: new Abstract: Although multi-modal learning has advanced point cloud completion, the theoretical mechanisms remain unclear. Recent works attribute success to the conn
arXiv:2601.17616v2 Announce Type: replace Abstract: Continual learning in Large Language Models (LLMs) is hindered by the plasticity-stability dilemma, where acquiring new capabilities often leads to
arXiv:2605.01905v1 Announce Type: cross Abstract: For the speaker-controlled spoken language identification task proposed in the TidyLang Challenge 2026, this paper proposes a language identification
arXiv:2605.00974v1 Announce Type: cross Abstract: LLMs are increasingly equipped with safety alignment mechanisms, yet recent studies demonstrate that they remain vulnerable to jailbreaking attacks th
arXiv:2601.08510v3 Announce Type: replace Abstract: Movie screenplays are rich long-form narratives that interleave complex character relationships, temporally ordered events, and dialogue-driven inte
arXiv:2605.02860v1 Announce Type: cross Abstract: Cross-language code clone detection (X-CCD) is challenging because semantically equivalent programs written in different languages often share little
arXiv:2605.02404v1 Announce Type: new Abstract: Model quantization has become essential for efficient large language model deployment, yet existing approaches involve clear trade-offs: methods such as
arXiv:2605.01653v1 Announce Type: new Abstract: We introduce SteeringDiffusion, a bottlenecked activation-level control interface for diffusion models that exposes a smooth, monotonic, and runtime-adj
arXiv:2602.08245v2 Announce Type: replace Abstract: Diffusion policies have recently emerged as a powerful paradigm for visuomotor control in robotic manipulation due to their ability to model the dis
arXiv:2504.17401v2 Announce Type: replace Abstract: Stereo disparity estimation is crucial for obtaining depth information in robot-assisted minimally invasive surgery (RAMIS). While current deep lear
arXiv:2605.02568v1 Announce Type: new Abstract: DeepSeek-V3.2 and V4 introduce Compressed Sparse Attention (CSA): a lightning indexer (a learned scoring projection over compressed keys) scores them, t
arXiv:2605.01939v1 Announce Type: new Abstract: Static benchmarks for LLMs are increasingly compromised by contamination and overfitting especially on knowledge intensive reasoning tasks While recent
arXiv:2605.00924v1 Announce Type: new Abstract: AI-generated content (AIGC) detectors are increasingly deployed in high-stakes settings such as academic integrity screening, yet their reliability rest
arXiv:2605.02209v1 Announce Type: cross Abstract: Evaluating large language models across many benchmarks is expensive, yet many benchmarks are highly correlated. We formalize the selection of a small