Knowledge catalogue
arXiv:2609.24678v1 Announce Type: cross Abstract: Continual learning with Low-Rank Adapters (LoRA) typically mitigates forgetting by penalizing the overlap between a new update and the accumulated pas
arXiv:2609.24441v1 Announce Type: new Abstract: Multivariate time-series forecasting is essential to many real-world applications. Recent large vision models (LVMs) offer a promising paradigm by trans
Must-read papers of the week ▪️ JEPA-Anything ▪️ Modality-Autoregressive World-Action Models ▪️ In-Context Robot Learning with VLM Agents ▪️ Dream-RSI: Recursive Self-Improvement through Evolving Worl
arXiv:2211.01566v2 Announce Type: replace-cross Abstract: This paper presents the applications of scientific ray-tracing in modeling and simulating light transport for space-borne image data generatio
arXiv:2602.09765v2 Announce Type: replace Abstract: Previous Vision-Language-Action models face critical limitations in navigation: scarce, diverse data from labor-intensive collection and static repr
arXiv:2609.24391v1 Announce Type: new Abstract: Voice-controlled interaction in industrial settings is hampered by acoustic noise, which severely degrades audio-only speech recognition. Audio-visual s
arXiv:2509.00754v3 Announce Type: replace Abstract: Dempster--Shafer theory (DST) provides an attractive framework for multi-source information fusion. However, its effectiveness critically depends on
arXiv:2609.24313v1 Announce Type: new Abstract: World models aim to capture environmental dynamics and predict future trajectories, showing growing potential for embodied intelligence. Physics-informe
arXiv:2609.23185v1 Announce Type: new Abstract: Lossy compression of scientific simulation data increasingly relies on learned, latent-space architectures such as Residual Vector Quantization (RVQ), w
arXiv:2609.23087v1 Announce Type: new Abstract: Modern Transformer design and compression both reduce to allocating capacity under a budget. The standard scalars for these decisions, #Params and #FLOP
• Ming-Image-0.1-Design, 6B • Ming-Image-0.1-Design-Layer, 6B • Two open-source Agent Skills: the Ling UI Design Skill and the Image-to-Editable-PPT Skill Ming-Image-0.1-Design ranks #1 among open-wei
Sessions are now a first-class unit of work in Arize AX. Annotate a whole conversation, queue it for review, and ask Alyx to filter for it — plus Agent-as-a-Judge on every plan, vision judges, faster
🚨NEW: @JTLonsdale & @SquawkCNBC clash on AI and wealth inequality. Joe Lonsdale: 2030s is the disinflation decade... we're all going to be really wealthy if we don't break this. Joe Kernen: Everybody'
New on Dedicated Model Inference: canary rollouts. Upgrade the model behind a live endpoint without downtime. Traffic moves from your current deployment to the new checkpoint in gated steps (default 5
This post is written by a human and I'd appreciate it if you treated it as such. Thanks. So, I've been noticing a pretty clear interest in developing as good a coding and agentic tool-calling model as
arXiv:2609.22774v1 Announce Type: new Abstract: This paper presents our system for Track 2 of the NLPCC 2026 Shared Task 10 on citation-level faithfulness in AI-assisted scientific reporting. Given an
arXiv:2609.22237v1 Announce Type: new Abstract: Merging low-rank adapters (LoRAs) promises to eliminate the overhead of swapping task-specific weights at inference time. However, existing merging meth
arXiv:2609.24517v1 Announce Type: cross Abstract: Model merging aims to combine multiple fine-tuned models derived from a common pretrained model into a single multi-task model without additional join
now on replicate: “Hot dog or not?” at 0.4 sec 🌭 jev-style decision model for image [glance-qwen3-vl-4b] now on huggingface and replicate: Demo: https://glancevlm.replit.app Replicate: https://replica
To build and deploy sophisticated robotics applications that can perceive, reason and act in dynamic environments, developers need new physical AI models and tools. The ROS open framework is a project
arXiv:2609.23856v1 Announce Type: new Abstract: Excessive force may damage tissue and increase the risk of anastomotic leakage in robotic colorectal surgery. Although the da Vinci 5 provides force sen
arXiv:2609.24155v1 Announce Type: new Abstract: Robot visuomotor policies are commonly formulated as autoregressive, diffusion-based, or more recently, flow matching models. Among them, Action-to-Acti
arXiv:2609.22133v1 Announce Type: new Abstract: In this paper, we show that LLM and human coding are observationally equivalent in terms of annotation quality: recent LLMs agree with expert coders at
arXiv:2603.05487v2 Announce Type: replace Abstract: Vision-Language-Action models (VLAs) have shown remarkable progress towards embodied intelligence. While their architecture partially resembles that
arXiv:2609.24195v1 Announce Type: new Abstract: Reliable perception is essential for underwater vehicles operating in complex environments, where light attenuation and scattering often degrade visibil
arXiv:2609.24703v1 Announce Type: cross Abstract: Data-driven protection may complement conventional relays in distribution grids whose operating conditions vary with distributed generation, switching
arXiv:2609.22289v1 Announce Type: new Abstract: Large-scale egocentric and whole-body human demonstrations are becoming a primary source of data for embodied intelligence. They record what people perc
Identity and access management company Okta Inc. used the opening day of its Oktane conference in Las Vegas today to announce runtime enforcement and a wider kill switch for its Okta for AI Agents pla
arXiv:2609.23417v1 Announce Type: cross Abstract: Screen-recorded web editing requests contain weak deictic expressions such as ``this'' and ``there,'' whose referents depend on speech, cursor traject
arXiv:2609.23088v1 Announce Type: new Abstract: Educational foundation models must solve problems, understand curriculum structure, diagnose learner difficulties, and provide appropriate instructional
arXiv:2609.22990v1 Announce Type: new Abstract: We study the symmetric and antisymmetric parts of bilinear forms in the attention heads of trained large language models. We introduce an orthogonally i
arXiv:2609.24504v1 Announce Type: new Abstract: Fine-tuned checkpoints and adapters now fill public repositories, and the most common operation applied to these artifacts is model merging: arithmetic
arXiv:2609.23819v1 Announce Type: cross Abstract: The Generalized Naive Bayes (GNB) model was introduced for discrete and categorical random variables as an extension of classic Naive Bayes. We now ac
arXiv:2604.01921v2 Announce Type: replace Abstract: Automotive radar perception pipelines commonly construct angle-domain representations via beamforming before applying learning-based models. This wo
arXiv:2609.22215v1 Announce Type: new Abstract: Knowledge distillation can transmit unintended behavioral traits from a teacher model to a student through training data that appear semantically unrela
arXiv:2507.21543v3 Announce Type: replace-cross Abstract: Mutual information regularization has recently been studied in reinforcement learning (RL) as an extension of entropy regularization, in which
arXiv:2609.23060v1 Announce Type: new Abstract: We study the online deployment of mobile ad hoc networks in unknown orthogonal environments, formalized as the Partially Observable Cooperative Guard Ar
arXiv:2609.23587v1 Announce Type: new Abstract: Large reasoning models (LRMs) incur high inference costs, often mitigated by efficiency techniques like quantization and pruning. However, the impact of
arXiv:2609.24377v1 Announce Type: cross Abstract: We study latent-space watermarking through a pretrained generator using a prescribed latent-to-output stochastic mapping, called the renderer. A water
arXiv:2609.22295v1 Announce Type: new Abstract: Event pipelines often discretize asynchronous timestamps before learning. This step looks harmless, but its stability depends directly on temporal resol
arXiv:2609.23686v1 Announce Type: new Abstract: Patch-based autoregressive time-series forecasting often ties input representation, learned transitions, and recursive execution to one patch length. We
arXiv:2609.23377v1 Announce Type: cross Abstract: Repository-level software engineering (SWE) comprises heterogeneous task categories, whose progress under pooled agentic reinforcement learning can be
arXiv:2609.23753v1 Announce Type: new Abstract: Generative world models aim to predict future states conditioned on actions, where action controllability is fundamental for reliable dynamics modeling.
arXiv:2609.24983v1 Announce Type: new Abstract: We present onPanda, an interactive tool for efficiently annotating LLM alignment data and agent trajectories. onPanda adopts token-level correction as i
arXiv:2609.23959v1 Announce Type: new Abstract: Screening a phone call for fraud needs a trustworthy probability after every caller turn, in milliseconds. Jev-style typed decisions promise exactly tha
Ming-Image-0.1-Design creates complete UIs, dashboards, infographics, and posters from structured prompts of up to 8K tokens, with consistent layouts, typography, colors, and imagery. It can also nati
David Gewirtz / ZDNET: OpenAI launches GPT-6 Sol and Luna, saying Sol makes about half as many mistakes as GPT-5.6 Sol and Luna matches GPT-5.6 Sol's performance at ~1% of the cost — GPT-6 Sol and Lun
Rachel Metz / Bloomberg: OpenAI says it plans to let third-party groups conduct technical safety evaluations of its AI models during the training, evaluation, and deployment phases — OpenAI plans to l
After turning a string of spectacular mathematical results into a reputational crisis, OpenAI is consulting human mathematicians to help it figure out a less disastrous path forward. On Monday, the co
arXiv:2609.22177v1 Announce Type: new Abstract: Tile-matching puzzle games serve hundreds of millions of players, yet the content-generation algorithms that decide which pieces to present at each turn
arXiv:2609.24253v1 Announce Type: cross Abstract: 3D Gaussian Splatting (3DGS) provides high-fidelity scenes for large-scale embodied simulation, but constructing large-scale urban assets remains cons
arXiv:2609.24202v1 Announce Type: new Abstract: Sparse attention reduces the quadratic cost of global self-attention while retaining strong empirical performance, but how its restricted interactions s
arXiv:2609.23968v1 Announce Type: new Abstract: Humanoid robots are expected to perform diverse human-level tasks in daily environments, many of which require precise regulation of interaction forces.
arXiv:2609.23308v1 Announce Type: new Abstract: Online controlled experiments, or A/B tests, are widely used to estimate causal effects on digital platforms. A central challenge is to improve experime
arXiv:2609.23265v1 Announce Type: new Abstract: We study repeated prophet inequalities under prefix feedback. In each of T rounds, a learner encounters fresh values drawn independently from n boxes wi
arXiv:2302.07477v4 Announce Type: replace Abstract: We study the optimal sample complexity of tabular reinforcement learning for infinite-horizon discounted Markov decision processes. The unrestricted
arXiv:2408.08823v2 Announce Type: replace Abstract: We develop a theoretical foundation for designing group-equivariant neural networks that align the choice of symmetries with the underlying probabil
arXiv:2609.23055v1 Announce Type: new Abstract: Discrete diffusion models now match autoregressive language models on several benchmarks, while the question of how best to train them has received far
Opus 5.5 is the best frontier model for parsing tables in PDFs. We ran it through ParseBench, and it scored 93.9%, a 7%+ increase over Opus 5, and beating Fable/Gemini/Astra. It's comparable to LlamaP
On 22 September 2026, Allie K. Miller posted on Twitter that the Opus 5.5 model led her to curse at Claude less frequently. She notes that while reducing profanity toward another AI is an undesirable