Knowledge catalogue
arXiv:2610.20965v1 Announce Type: new Abstract: Large multimodal models have achieved remarkable progress by scaling model capacity and training on massive paired multimodal data. However, this paradi
arXiv:2610.22086v1 Announce Type: cross Abstract: Supervised fine-tuning datasets remain overwhelmingly English-centric and commercially restricted, as their content is frequently generated by proprie
arXiv:2610.22294v1 Announce Type: new Abstract: Few-shot prompting is useful when instructions and rewards are hard to specify. One such application is editing by example, where a demonstrated formatt
arXiv:2610.21573v1 Announce Type: new Abstract: Decision trees can make vision-language model (VLM) classification interpretable by replacing a single prediction with a sequence of root-to-leaf questi
arXiv:2609.08183v2 Announce Type: replace Abstract: Recursive self-improvement (RSI) requires a concrete mechanism through which an AI system observes its capabilities and converts that evidence into
arXiv:2610.21679v1 Announce Type: new Abstract: Tokenization is a critical component of the language modeling pipeline, but it is poorly understood. Tokenizers can impact downstream performance, but t
arXiv:2610.20993v1 Announce Type: new Abstract: Reordering multiple-choice options can change a model's answer, an effect studied as selection bias (a preference for certain option letters) and as ord
arXiv:2610.21983v1 Announce Type: new Abstract: Learning from experience requires recovering reusable knowledge and determining when it applies to a new situation. We introduce OntoAct, a hypothesis-b
arXiv:2610.22200v1 Announce Type: new Abstract: Computer use has reached a turning point: the focus is expanding from GUI-only interaction to systems that complete tasks on users' computers through vi
arXiv:2610.21496v1 Announce Type: new Abstract: Reliable repository-level coding requires agents not only to generate correct code but also to preserve constraints and respond to tool feedback across
arXiv:2603.16122v2 Announce Type: replace Abstract: Out-of-distribution (OOD) objects are often silently overlooked by object detectors, which produce no detection for them, leaving downstream modules
arXiv:2610.21979v1 Announce Type: cross Abstract: End-to-end full-page document parsing must preserve the content and structure of heterogeneous elements, yet otherwise accurate outputs can contain lo
arXiv:2610.22358v1 Announce Type: new Abstract: Time series foundation models are becoming increasingly popular for general-purpose forecasting. However, most leading models predict marginal quantiles
Pay attention to this new wave of VLMs. Glimpse is the first model from @ElorianAI, the brains that led Google's Gemini and Apple's MM-1. Quick test: 10 game boards from an overhead camera. Same promp
arXiv:2610.20830v1 Announce Type: new Abstract: Phonetic error detection (PED) aims to identify phoneme-level substitutions, deletions, and insertions and is essential for educational and clinical spe
arXiv:2610.21134v1 Announce Type: new Abstract: Predicting live birth before fresh embryo transfer could support shared decision-making in IVF/ICSI, but routine clinical data are small, heterogeneous,
arXiv:2610.21046v1 Announce Type: cross Abstract: Peer review is under strain from the growth of submissions, and review comments written by humans or AI can misstate what a paper says. We introduce R
arXiv:2610.22158v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have substantially improved Text-to-SQL performance, yet existing NL2SQL systems largely assume that use
arXiv:2610.22019v1 Announce Type: cross Abstract: Frontier models, general-purpose and domain-specific alike, now include a midtraining stage between pretraining and post-training, but little has been
arXiv:2610.20628v1 Announce Type: new Abstract: Multi-agent systems (MAS) based on large language models (LLMs) have become a powerful way to address complex problems, and their effectiveness depends
arXiv:2610.20796v1 Announce Type: cross Abstract: Health-misinformation analysis presents a dual challenge: misleading claims can affect public well-being, while systems designed to detect them may ex
arXiv:2610.21764v1 Announce Type: new Abstract: A fixed discount factor in Q-learning imposes a single planning horizon throughout training, despite the differing demands of early exploration and long
arXiv:2610.21512v1 Announce Type: new Abstract: DeepSearch agents achieve strong performance on complex information-seeking tasks through iterative search and reasoning. However, they often issue inte
arXiv:2610.20739v1 Announce Type: new Abstract: Quantile forecasts summarize uncertainty at each future time step, while diffusion forecasters represent it through sampled future trajectories. We stud
arXiv:2610.21344v1 Announce Type: new Abstract: Resting-state functional connectivity is widely used in machine learning-based classification of neuropsychiatric disorders. Quantum machine learning mo
arXiv:2607.18915v2 Announce Type: replace Abstract: With the rapid advancement of large language models (LLMs), modern systems not only possess strong foundational capabilities and extensive knowledge
arXiv:2610.20781v1 Announce Type: cross Abstract: Image-to-text (I2T) understanding and text-to-image (T2I) generation are dual tasks in unified multimodal models (UMMs). Reconstructive post-training
arXiv:2610.21220v1 Announce Type: cross Abstract: Recommender systems often need to balance multiple conflicting objectives. Controllable Multi-Objective Recommendation (CMOR) enables dynamic adjustme
Beam is an open model built by Reflection. Beam takes text as input and generates text as output. This release includes the instruction-tuned model in BF16, FP8, and NVFP4 numerics. Beam uses a sparse
arXiv:2610.21539v1 Announce Type: new Abstract: Diffusion models (DMs) have steadily demonstrated outstanding performance in high-fidelity, controllable generation across diverse scenarios, following
arXiv:2610.21189v1 Announce Type: new Abstract: Instruction-following language models can comply with requests that conflict with intended behaviors and safety alignment. We introduce a training-free
arXiv:2610.21287v1 Announce Type: new Abstract: Training-free object removal commonly redirects self-attention away from the target region, but on few-step distilled diffusion models this often leaves
arXiv:2602.05785v2 Announce Type: replace-cross Abstract: Generalizable image-based person re-identification (Re-ID) aims to recognize individuals across cameras in unseen domains without retraining.
arXiv:2610.21262v1 Announce Type: new Abstract: Learning from label proportions (LLP) is a weakly supervised setting where training data are grouped into bags with only bag-level label proportions obs
arXiv:2610.22051v1 Announce Type: cross Abstract: In the best-arm identification problem, an algorithm adaptively selects arms to find the arm of the largest mean reward. Successive Rejects (SR) is a
arXiv:2610.21571v1 Announce Type: cross Abstract: Large language model (LLM) agents solve complex tasks by calling external tools over multiple turns. Recent work has proposed tool graph memory, which
arXiv:2610.21090v1 Announce Type: new Abstract: We present RoboCloth, a dataset of 500 real cloth materials captured under flexible, calibrated camera and lighting configurations, where both are robot
arXiv:2610.20686v1 Announce Type: new Abstract: Multi-head latent attention (MLA) compresses the content of a key-value cache into a shared latent per token, making low-bit storage attractive for long
arXiv:2610.21086v1 Announce Type: new Abstract: Camera-to-robot pose estimation from a monocular image is significant for vision-based robot navigation and control. However, recovering 3D structural f
arXiv:2610.20959v1 Announce Type: cross Abstract: Answering questions over heterogeneous data means combining evidence from files, databases, documents and the web. Data agents automate this, but thei
arXiv:2610.21370v1 Announce Type: new Abstract: Neural PDE solvers commonly generate multi-step predictions through autoregressive rollout, recursively applying a learned evolution operator and feedin
arXiv:2610.21367v1 Announce Type: new Abstract: Test-time adaptation (TTA) mitigates the performance degradation of source-pretrained models on unlabeled test data under distribution shifts. Recent ba
arXiv:2610.22094v1 Announce Type: new Abstract: Contrastive vision-language pre-training supports zero-shot chest X-ray diagnosis, but standard objectives treat every off-diagonal image-report pair in
arXiv:2610.21642v1 Announce Type: new Abstract: Vision Transformer architectures have showcased impressive performance on semantic segmentation, yet their quadratic attention complexity hinders practi
🆕 show: HIGH TASTE TESTERS We convene top Al power users to compare what actually works-and what falls apart once you start using it.@davis7, @benhylak, @dexhorthy, @allisonology, @altryne and @swyx g
arXiv:2610.20866v1 Announce Type: cross Abstract: Realistic traffic simulation and autonomous planning both depend on modeling interactions among heterogeneous road users whose dynamics, constraints,
arXiv:2610.22337v1 Announce Type: new Abstract: Robotic harvesting requires precise manipulation to ensure accurate positioning of the end-effector, especially in a constraint workspace. This study in
arXiv:2610.21440v1 Announce Type: new Abstract: In automatic speech recognition (ASR), transcription errors with similar lexical or semantic discrepancies can have markedly different consequences for
arXiv:2610.22217v1 Announce Type: cross Abstract: Reinforcement learning (RL) can elicit specialized visual capabilities in vision-language models (VLMs), yet jointly optimizing heterogeneous objectiv
arXiv:2610.20788v1 Announce Type: new Abstract: Compact representations that support geometrically meaningful comparisons are valuable for learning from probability distributions. We study optimal, fr
arXiv:2602.03737v2 Announce Type: replace Abstract: Monitoring bottom-hole variables in petroleum wells is essential for production optimization, safety, and emissions reduction. Permanent Downhole Ga
arXiv:2610.20968v1 Announce Type: cross Abstract: Executing heavy-duty physical manipulation in unpredictable environments remains a major challenge for quadrupedal robots lacking dedicated manipulato
arXiv:2610.21207v1 Announce Type: new Abstract: Point-cloud streams are central to autonomous driving and robotics, yet existing segmentation networks process every frame from scratch, although consec
arXiv:2610.22342v1 Announce Type: new Abstract: Generalist robot policies benefit from large-scale visual pretraining but often struggle with contact-rich dexterous manipulation, where force, complian
arXiv:2610.21621v1 Announce Type: new Abstract: Recent Vision-Language Models (VLMs) enable automated preference labeling for robotic manipulation, yet their deployment remains impractical since each
arXiv:2610.21312v1 Announce Type: new Abstract: Data-free preconditioning builds the Kronecker factors of KFAC from synthetic probes instead of private data. DP-KFC validates a probe by matching the e
arXiv:2507.19839v2 Announce Type: replace-cross Abstract: The modality gap is intrinsic to multimodal alignment, where embeddings from different modalities remain partially separated in a shared repre
arXiv:2610.20960v1 Announce Type: new Abstract: Safety in agentic systems is inherently sequential: whether an action is safe depends on prior actions, tool outputs, information disclosures, and inter
arXiv:2610.21156v1 Announce Type: new Abstract: Proactive dialogue agents must guide multi-turn interactions toward task goals while adapting to users whose intentions and attitudes evolve. Existing p
arXiv:2610.22242v1 Announce Type: cross Abstract: Tabular foundation models (TFMs) now outperform gradient-boosted trees in classification and regression. Yet in survival analysis, which predicts when