Knowledge catalogue
arXiv:2609.37494v1 Announce Type: new Abstract: Multiple-choice benchmarks are cheap to grade and are running out of room, and the standard remedy, writing harder items, is slow and repeated for every
arXiv:2609.37883v1 Announce Type: new Abstract: Pre-trained language models (PLMs) with encoder-based architectures have shown impressive capabilities in zero-shot cross-lingual transfer for various l
arXiv:2609.34035v1 Announce Type: new Abstract: Tracking any point of a dynamic scene in metric 3D - in absolute meters, not up to an unknown scale - underpins 3D and 4D reconstruction, robot navigati
arXiv:2609.31756v1 Announce Type: new Abstract: Does high image fidelity imply readable screen content in 3D Gaussian Splatting (3DGS)? We introduce 3DGS-SC, a controlled static screen-content dataset
I wanted a fun way to visualize and stress-test a multi-agent ecosystem, so I pointed it at my favorite MMO (a vanilla-era private server emulator). Live view: https://design.kristiantalley.com/projec
I’m building a Polish General purpose legal Model that drafts documents, answers questions using legal sources, and has enough coding ability to handle some automation. The workflow is very tool-heavy
arXiv:2609.33467v1 Announce Type: new Abstract: When post-training large language models on tasks with semi-verifiable rewards, there are many factors (training steps, base model size, training order,
arXiv:2609.32341v1 Announce Type: new Abstract: Transformers and state-space models (SSMs) are two prominent sequential learning architectures, yet their comparison remains largely empirical and exist
arXiv:2609.33457v1 Announce Type: new Abstract: Many dense-prediction benchmarks evaluate rare events by pooling prediction and target over spatial blocks, thresholding each, and scoring the contingen
arXiv:2609.32890v1 Announce Type: new Abstract: Language models are increasingly evaluated as vulnerability detectors, and scores reported for similar models differ widely between papers. We measured
arXiv:2609.31877v1 Announce Type: cross Abstract: Cloud-based Large language model (LLM) services create a network-level traffic side channel that can expose model, prompt, and task behavior despite e
arXiv:2609.33424v1 Announce Type: cross Abstract: Self-supervised pretraining learns representations that are broadly transferable across downstream tasks, yet direct fine-tuning can be suboptimal due
arXiv:2609.33991v1 Announce Type: new Abstract: Weed detection is an important component of precision agriculture, enabling site-specific weed management and reducing unnecessary herbicide use. Althou
arXiv:2609.31821v1 Announce Type: new Abstract: Developing label-efficient models is a central challenge in surgical AI due to the high cost and scarcity of expert annotation. While self-supervised fo
arXiv:2609.32149v1 Announce Type: cross Abstract: Linear bandits model sequential decision-making problems with noisy rewards that are linear in the decision variable, where an agent must simultaneous
When scaling up agentic reinforcement learning (RL) and evaluation across massive parallel rollouts, frontier AI labs inevitably hit a bottleneck: Expensive GPU clusters sit idle, waiting minutes for
arXiv:2602.20502v2 Announce Type: replace-cross Abstract: Many web agents operate through a reactive execution loop: they observe the current interface, reason about the next action, execute it, and r
arXiv:2609.34547v1 Announce Type: new Abstract: Video-capable vision-language models score above 80% on popular benchmarks yet struggle with spatial-temporal binding: associating the right action with
arXiv:2609.31675v1 Announce Type: new Abstract: We introduce the Active Causal Discovery Benchmark (ACDB), an SCM-grounded environment for evaluating whether LLM agents recover causal graph structure
arXiv:2609.32325v1 Announce Type: new Abstract: In many prediction tasks, acquiring all features can be a prohibitively expensive or outright impossible task. Further, in many cases a static subset of
arXiv:2609.34085v1 Announce Type: cross Abstract: Autonomous driving requires extit{world models} that can understand the physical world, reason and plan, and operate safely. In this paper, we first s
arXiv:2609.31690v1 Announce Type: new Abstract: Explainable Artificial Intelligence (XAI) solutions are essential for building trust in AI technologies and their integration in real manufacturing line
arXiv:2609.32976v1 Announce Type: new Abstract: Incorrect or corrupted labels in tabular datasets can significantly degrade supervised learning performance, particularly when mislabeling is subtle and
arXiv:2005.08844v3 Announce Type: replace Abstract: We apply entropy to reinforcement learning in two ways: entropy-augmented reward defines the soft objective, while relative-entropy regularization c
arXiv:2609.35212v1 Announce Type: new Abstract: Multi-view clustering aims to capture cross-view consistency while exploiting view-specific information. However, shared representations learned to capt
arXiv:2609.33230v1 Announce Type: new Abstract: FMCW LiDAR measures per-point radial Doppler velocity alongside range, providing a motion cue unavailable in conventional time-of-flight sensors. Exploi
arXiv:2609.34683v1 Announce Type: new Abstract: The optimization of LLM serving engines, such as vLLM and SGLang, is largely benchmark-driven: optimizations, scheduling policies, hardware and system d
arXiv:2609.32478v1 Announce Type: cross Abstract: We study smoothed online prediction with bounded adversarial responses. This widely studied framework bridges i.i.d. sampling and adversarial covariat
arXiv:2609.35257v1 Announce Type: new Abstract: Zeroth-order (ZO) optimization offers a memory-efficient alternative for LLM fine-tuning by estimating updates only from forward evaluations of perturbe
arXiv:2609.33728v1 Announce Type: new Abstract: Reliable world models should not only predict future states but express how actions change the world in an explicit, transparent and testable form, such
arXiv:2609.34962v1 Announce Type: new Abstract: Estimating mutual information (MI) from samples is a central objective in a variety of scientific fields. Modern neural estimators are accurate in the l
arXiv:2609.34467v1 Announce Type: new Abstract: Recent advances in Vision-Language-Action (VLA) models point toward general-purpose robotic intelligence by unifying perception, instruction, and contro
arXiv:2609.32913v1 Announce Type: new Abstract: Recent progress in frontier models has renewed interest in large-scale reinforcement learning (RL), but the cost of generating large-model rollouts make
arXiv:2609.32527v1 Announce Type: cross Abstract: Predicting cellular responses to genetic perturbations helps prioritize experiments in single-cell genomics, where exhaustive measurement is infeasibl
arXiv:2609.32041v1 Announce Type: new Abstract: Modern Document AI reads contracts, extracts fields, reasons over tables, and grounds answers to page regions, then forgets everything. Processing an am
arXiv:2609.32178v1 Announce Type: new Abstract: Rotary position encodings make attention sensitive to relative position, but extending them to graphs requires choosing how graph structure enters the r
arXiv:2609.32602v1 Announce Type: new Abstract: Adversarial attacks optimized on a single open-weight LLM can transfer to and jailbreak architecturally different models, allowing an attacker with whit
arXiv:2609.33814v1 Announce Type: cross Abstract: We characterize Bregman Douglas-Rachford splitting (BDRS) for unregularized discrete optimal transport and develop an anytime primal-dual certificate
Anthropic: Anthropic says GLM-5.3 can autonomously build end-to-end cyber exploits, like Claude Mythos Preview, but was released without robust safeguards against misuse — GLM-5.3 can develop working
Opus 5.5 dropped em dashes from 12.9 per 1,000 words to two in 57,000 words, and cut the rest of the Claudisms in half. Better, but not fixed. The post Anthropic says it fixed Claude’s writing. I ran
In its pending IPO prospectus, Anthropic disclosed that advancing AI models could pose “existential risks to humanity,” highlighting potential for unintended behaviors such as manipulation and blackma
arXiv:2609.32248v1 Announce Type: new Abstract: Large language model (LLM) leaderboards compare model capabilities by ranking models according to their mean performance on fixed benchmarks. However, v
arXiv:2609.33193v1 Announce Type: new Abstract: How many directions in weight space does training need? The intrinsic dimension answers this with the smallest number of random directions in which trai
arXiv:2609.33299v1 Announce Type: new Abstract: World Action Models (WAMs) are becoming increasingly important and useful for embodied intelligence, as they enable robots to anticipate the consequence
arXiv:2609.34047v1 Announce Type: new Abstract: Multimodal models increasingly interpret visual environments, but their ability to recognize the same building across photographs, floor plans, elevatio
arXiv:2605.06643v2 Announce Type: replace Abstract: Despite the growing popularity of Multimodal Domain Generalization (MMDG) for enhancing model robustness, it remains unclear whether reported perfor
arXiv:2609.34484v1 Announce Type: cross Abstract: Progress reward modeling is the problem of estimating how a robot's behavior changes task progress over time. Reliable estimation requires distinguish
arXiv:2609.33931v1 Announce Type: cross Abstract: Modern methods reconstruct or generate simulation-ready articulated objects, predicting not only their geometry but also how their parts are connected
arXiv:2509.25570v2 Announce Type: replace Abstract: Vision Graph Neural Networks (ViGs) have demonstrated promising performance in image recognition tasks against Convolutional Neural Networks (CNNs)
arXiv:2609.32567v1 Announce Type: new Abstract: LAOD and similar zero-training LLM+open-vocabulary-detector (OVOD) pipelines score two things separately: class-agnostic localization accuracy (CAAP) an
arXiv:2507.02915v2 Announce Type: replace-cross Abstract: Building on the Joint-Embedding Predictive Architecture (JEPA) paradigm, a recent self-supervised learning framework that predicts latent repr
arXiv:2609.33891v1 Announce Type: new Abstract: Multicalibration requires a predictor's residuals to be unbiased not only globally, but also after conditioning on the predictor's own level sets and re
arXiv:2506.02914v3 Announce Type: replace Abstract: The contemporary paradigm of scaling data annotation, crucial for developing machine learning solutions, is to hire ordinary human annotators and in
arXiv:2609.33392v1 Announce Type: new Abstract: Hypergraph neural networks have achieved significant success in recent years. However, manual architecture crafting is labor-intensive and often fails t
arXiv:2609.35420v1 Announce Type: new Abstract: Wildlife conservation involves protecting, preserving, and managing wildlife species and their habitats. With today's rapid pace of human development, c
arXiv:2609.33802v1 Announce Type: cross Abstract: Understanding quantum phases of matter has long relied on physicists' intuition and mathematical tools such as symmetry and topology. Remarkably succe
arXiv:2609.31683v1 Announce Type: new Abstract: This work presents an end-to-end demonstration of autonomous machine learning research conducted by an agent skill on consumer hardware. The demonstrati
arXiv:2609.35530v1 Announce Type: new Abstract: Recent image generation models can take multiple reference images as input and combine them into a new image. However, multi-reference image generation
arXiv:2609.31848v1 Announce Type: new Abstract: The Gromov-Wasserstein (GW) distance measures the discrepancy between metric measure (mm) spaces and identifies optimal alignments between them based so
ci : update the oneAPI toolkit to 2026.1 (#29273) ci : update the oneAPI toolkit to 2026.1 oneDNN is removed from Intel Deep Learning Essentials in 2026.0, so staying on the deep-learning-essentials p