Knowledge catalogue
arXiv:2605.29873v1 Announce Type: new Abstract: Key-Value (KV) cache remains a major bottleneck for deploying Large Language Models (LLMs) in long-generation tasks. Prior work often applies uniform co
arXiv:2605.29033v1 Announce Type: new Abstract: Score-based and flow-based generative models exhibit remarkable expressive capacity in capturing complex distributions, and have been extensively deploy
Most people training agentic LLMs with RL right now have a silently broken training loop and have no idea. Here's the trap: single-turn RL works beautifully. Clean curves, sane rewards, everything con
arXiv:2601.05149v2 Announce Type: replace Abstract: Autoregressive (AR) models have achieved remarkable success in image synthesis, yet their sequential nature imposes significant latency constraints.
arXiv:2605.30347v1 Announce Type: new Abstract: Data-driven approaches have revolutionized 3D vision, enabling transformers to effectively reconstruct and generate static 3D objects. However, generati
arXiv:2605.29592v1 Announce Type: new Abstract: Class-Incremental Learning (CIL) with pre-trained models (PTMs) aims to sequentially adapt PTMs to new categories without forgetting old knowledge. Buil
Nvidia up 0.7%, on news that tokenmaxxing is dead and H200 rental prices are down. What an absurd time to be alive. In the last 30 days alone: – Microsoft cancelled most of its Claude Code licenses, c
arXiv:2510.10961v3 Announce Type: replace-cross Abstract: As language models become increasingly deployed in online environments, toxicity detection and detoxification have received growing attention.
arXiv:2605.29250v1 Announce Type: cross Abstract: Real-world information needs require access to structurally diverse knowledge sources, from unstructured text and relational tables to knowledge graph
On the remarkable return on capital potential for Starlink on Starship. Including customer acquisition cost, ground station capex, and an expendable top stage, we think SpaceX should be able to launch
arXiv:2605.29575v1 Announce Type: new Abstract: Rapid identification of damaged buildings after natural disasters or on war areas is crucial to support emergency response and prioritize interventions.
arXiv:2603.14778v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) enables large language models to use external knowledge, but outsourcing the RAG service raises privacy c
arXiv:2605.29058v1 Announce Type: new Abstract: Bayesian Networks (BNs) are of interest from an explainable AI viewpoint, offering transparent probabilistic models for decision support. Baymex is a re
arXiv:2605.30126v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) map visual inputs into dense token sequences, imposing a quadratic computational bottleneck for inference. Elasti
Parse PDFs in the browser, or the edge, in milliseconds Our LiteParse WASM package can be literally run anywhere, from cloudflare workers, mobile runtimes, to the browser. Starter template for Cloudfl
arXiv:2605.29486v1 Announce Type: cross Abstract: A central bottleneck for phone-use agents is that controllable, reproducible environments covering real mobile behavior are hard to build at scale. Ex
pibot is now running fully local, using parakeet for STT, qwen3-tts for TTS, and Qwen 3.6 as the local multi-modal LLM via llama.cpp. The STT and TTS inference engines are Rust/mlx-c based. Ported fro
arXiv:2605.29563v1 Announce Type: new Abstract: Can VLMs predict how each camera move changes the view, and plan many such moves ahead? We call this capability view planning, requiring (1)understandin
arXiv:2506.08354v2 Announce Type: replace-cross Abstract: This position paper argues that text embedding research should move beyond surface meaning and embrace implicit semantics as a central modelin
This guide introduces torch.profiler, PyTorch's built-in profiling tool for analyzing model performance and identifying computational bottlenecks. It covers the basics of using the profiler to measure
arXiv:2605.30054v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to generate software artifacts across many software engineering (SE) tasks, yet ensuring the semant
This article discusses security measures and best practices for protecting AI model inference endpoints from unauthorized access and theft, likely covering topics such as API authentication, rate limi
arXiv:2605.29251v1 Announce Type: new Abstract: As large language models transition from bounded generative engines to agents with expansive execution privileges, AI going out of control precipitates
arXiv:2605.30075v1 Announce Type: new Abstract: Quantum Federated Learning (QFL) offers a promising framework to train quantum models across distributed clients while keeping data strictly local. Due
arXiv:2605.30029v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) systems expose numerous design choices spanning query rewriting, chunking, retrieval depth, reranking, and context
arXiv:2605.29893v1 Announce Type: new Abstract: LLM-based agents have demonstrated strong capabilities in solving complex tasks through multi-step reasoning and tool use. However, existing evaluation
arXiv:2605.29634v1 Announce Type: new Abstract: Transformer hidden states are often interpreted through local or low-order objects: neurons, sparse features, attention heads, residual-stream direction
arXiv:2605.28870v1 Announce Type: cross Abstract: We investigate the Platonic Representation Hypothesis (PRH) through a tripartite statistical framework of representations: signal, bias, and noise. {1
arXiv:2605.28850v1 Announce Type: new Abstract: We study behavioral alignment and representation dynamics of large language model (LLM) agents in financial decision environments. Using TradeArena, an
arXiv:2605.28962v1 Announce Type: new Abstract: Diffusion bridge models offer a powerful framework for connecting two data distributions, such as in image restoration and translation. Many existing me
arXiv:2605.29234v1 Announce Type: new Abstract: We study large-scale literature search from two complementary angles: improving the retrieval pipeline, and stress-testing the human reference list as a
arXiv:2605.30326v1 Announce Type: cross Abstract: The ability to reason, adapt, and creatively solve problems under unexpected challenges is essential for robots operating in real-world environments.
arXiv:2605.29662v1 Announce Type: new Abstract: Real-time inference of vision-language-action (VLA) models is essential for robotic control. While visual token pruning has shown strong potential for a
arXiv:2509.23694v5 Announce Type: replace Abstract: Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date information. However, this also introduces a new thr
Salesforce published a detailed writeup on going agentic with Claude Code. A couple things jumped out. A migration they'd scoped at 231 days shipped in 13. One PR delivered 21 endpoints at 100% test c
arXiv:2605.29084v1 Announce Type: cross Abstract: A retrieval-augmented generation (RAG) system deployed over a multi-author institutional corpus can give a different answer to the same question depen
arXiv:2605.29916v1 Announce Type: cross Abstract: The Random Gradient hyper-heuristic was recently shown to be able to learn the optimal neighbourhood size when optimizing the LeadingOnes benchmark vi
arXiv:2605.30290v1 Announce Type: cross Abstract: Self-improvement at scale has been a longstanding goal for reasoning models, and there are two natural places to do it: at test time, through verifica
arXiv:2605.30116v1 Announce Type: new Abstract: Distribution Matching Distillation (DMD) is a widely used paradigm for accelerating inference in few-step video diffusion models. However, DMD-style vid
arXiv:2603.17945v2 Announce Type: replace Abstract: In multilingual pretraining, the test loss of a pretrained model is heavily influenced by the proportion of each language in the pretraining data, n
arXiv:2602.01869v3 Announce Type: replace Abstract: LLM-driven agents excel at sequential decision-making but often rely on on-the-fly reasoning, re-deriving solutions even in recurring scenarios. Thi
arXiv:2605.29794v1 Announce Type: new Abstract: LLM agents now draw on growing skill libraries to handle complex tasks. However, injecting more skills does not always improve task completion and can e
arXiv:2605.29188v1 Announce Type: new Abstract: Dictionary methods, topic models, and embedding-similarity scorers are widely used in CSS and management research to measure constructs such as 'entrepr
arXiv:2605.29863v1 Announce Type: new Abstract: Predicting the next mobile application a user will launch is essential for intelligent device resource management and proactive assistance. Existing mod
arXiv:2603.13249v2 Announce Type: replace-cross Abstract: Activation steering offers a computationally efficient mechanism for controlling Large Language Models (LLMs) without fine-tuning. While effec
OpenAI launches Rosalind Biodefense, expanding trusted access to GPT-Rosalind for vetted developers and U.S. government partners advancing biodefense, public health, and pandemic preparedness through
arXiv:2605.29954v1 Announce Type: new Abstract: Sparse vision transformers have gained popularity as efficient encoders for medical volumetric segmentation, with Swin emerging as a prominent choice. S
arXiv:2512.10388v2 Announce Type: replace-cross Abstract: Conventional Sequential Recommender Systems (SRS) typically assign unique hash IDs (HID) to construct item embeddings, which mainly capture co
arXiv:2605.28843v1 Announce Type: cross Abstract: AI is transforming life sciences research at unprecedented speed, accelerating discovery across protein structure prediction, genome modeling, and dru
The blast bent those steel beams on the tower inwards: First look at LC-36 from the air this morning after the explosion of New Glenn last night during a failed hotfire test. Visible is the wreckage f
arXiv:2605.28983v1 Announce Type: cross Abstract: In this paper, training a neural network is identified, exactly, as a search through Hamilton--Jacobi initial-value problems: each gradient step selec
The improvements run wide. Across all major European languages, Command A+ consistently pulls ahead of competitors on WMT24++ (xCOMET-XL): 🇫🇷 +2.4 pts in French 🇪🇸 +1.9 pts in Spanish 🇩🇪 +0.9 pts in G
arXiv:2605.29301v1 Announce Type: new Abstract: The Open Motion Planning Library (OMPL), first released in 2008, has become a cornerstone of the motion planning community, providing implementations of
The story gets bigger beyond Europe. Command A+ makes major gains in high-impact non-Latin languages; outperforming Mistral Medium 3.5 in Korean, Japanese, Hebrew, Chinese, and Arabic. For Arabic, tha
The team at @llama_index built an awesome template using LlamaParse and the new Managed Agents in the Gemini API. See how they built an agent that can tackle unstructured documents. 📄↓ 🚀 The team at @
arXiv:2605.29652v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly being used to generate health text from structured records such as wearable time series, biomarkers, vital
this was my pypi hardening strategy for @activegraphai: - spin up a new @replit - point at docs page, ask it to build something - ask it to write a feedback report to package builder - feed that feedb
arXiv:2605.29183v1 Announce Type: cross Abstract: As machine learning(ML) systems evolve to continual adaptation, each re-training cycle uses compute, annotation, and energy. We introduce TIMEGATE, a
arXiv:2605.29380v1 Announce Type: cross Abstract: Mainstream strategies for finetuning pretrained multimodal models often degrade out-of-distribution (OOD) robustness, a phenomenon known as catastroph
arXiv:2605.29153v1 Announce Type: cross Abstract: Neural networks trained under different hyperparameter settings can fall into distinct training 'regimes,' with consistent behavior within regimes and