Knowledge catalogue
arXiv:2605.20531v1 Announce Type: cross Abstract: Reliable verification of proofs remains a bottleneck for training and evaluating AI systems on hard mathematical reasoning. Fully formal proofs, in la
arXiv:2602.01273v4 Announce Type: replace Abstract: Recently, Diffusion Transformers (DiTs) have emerged in Real-World Image Super-Resolution (Real-ISR) to generate high-quality textures, yet their he
arXiv:2605.21486v1 Announce Type: new Abstract: Hyperparameter transfer allows extrapolating optimal optimization hyperparameters from small to large scales, making it critical for training large lang
arXiv:2510.00171v2 Announce Type: replace-cross Abstract: We investigate quantum reservoir computing (QRC) using a hybrid qubit-boson system described by the Jaynes-Cummings (JC) Hamiltonian and its d
arXiv:2512.09447v2 Announce Type: replace-cross Abstract: Structurally repetitive environments produce visually plausible but aliased LiDAR loop candidates that can destabilize pose-graph optimization
Vercel has announced the availability of Qwen 3.7 Max, a language model, through its Vercel AI Gateway platform. This integration allows developers to access and use Qwen 3.7 Max alongside other AI mo
arXiv:2605.20584v1 Announce Type: new Abstract: Mobile app marketplaces require developers to disclose standardized content rating descriptors (CRDs) to inform users about potentially sensitive or res
arXiv:2508.03578v2 Announce Type: replace Abstract: Radar-based human pose estimation enables privacy-preserving motion tracking for ambient intelligence, yet the noisy nature of radar sensing makes u
arXiv:2605.21195v1 Announce Type: new Abstract: Discrete autoregressive (AR) text-to-image (T2I) models pair a VQ tokenizer with an AR policy, and current post-training pipelines optimize only the pol
arXiv:2605.21112v1 Announce Type: new Abstract: 4D automotive radar is indispensable for autonomous driving due to its low cost and robustness, yet its point cloud sparsity challenges 3D object detect
arXiv:2605.20809v1 Announce Type: new Abstract: While Large Language Models (LLMs) demonstrate remarkable performance on zero-shot annotation tasks, they often struggle with the specialized convention
arXiv:2605.20506v1 Announce Type: cross Abstract: Humans learn social norms and behaviors from verbal feedback (e.g., a parent saying 'that was rude' or a friend explaining 'here's why that hurt'). Ye
arXiv:2605.20262v1 Announce Type: new Abstract: We study selective refusal editing as a three-way control problem: induce non-refusal on designated edit prompts while preserving benign behavior and ha
arXiv:2605.20737v1 Announce Type: new Abstract: Existing approaches for unsupervised 3D point cloud segmentation predominantly rely on a purely visual similarity-based learning-by-clustering paradigm,
arXiv:2605.20626v1 Announce Type: new Abstract: We present the University of Florida Gators submission to the AmericasNLP 2026 shared task on cultural image captioning for Indigenous languages. Our tw
arXiv:2605.21066v1 Announce Type: new Abstract: Recommender systems often rely on observational user--item interaction data, which is prone to selection bias due to users' selective interactions with
arXiv:2605.21429v1 Announce Type: cross Abstract: Tactile-based reinforcement learning (RL) is currently hindered by fragmented research and a focus on over-saturated orientation tasks. We introduce v
arXiv:2605.20868v1 Announce Type: new Abstract: KV cache quantization reduces the memory cost of long-context LLM inference, but introduces approximation error that is typically validated only empiric
arXiv:2605.21138v1 Announce Type: new Abstract: Smoothed implicit contact dynamics enables gradient-based planning and control for contact-rich tasks without predefined mode sequences. However, safety
arXiv:2605.20645v1 Announce Type: new Abstract: Foggy conditions are commonly encountered in real-world applications; however, existing action recognition approaches typically assume favorable weather
Seems GPT-5.2 reaches expert level in peer review: 45 scientists took 469 hours evaluating human & AI reviews on 82 papers. 'Surprisingly, current AI reviewers are competitive even with the top-rated
Self-Evolving in the Wild：Over the course of ~35 hours of continuous autonomous execution, the model performed 432 kernel evaluations across 1,158 tool calls. It wrote, compiled, profiled, and iterati
arXiv:2605.21341v1 Announce Type: cross Abstract: Functional bilevel methods estimate a lower-level function and plug it into a hypergradient, but this plug-in gradient can retain first-order bias whe
arXiv:2509.13648v3 Announce Type: replace Abstract: Generative recommendation plays a crucial role in personalized systems, predicting users' future interactions from their historical behavior sequenc
arXiv:2605.20510v1 Announce Type: new Abstract: Urban heat exposure is becoming an increasingly critical challenge due to the intensifying urban heat island effect. Fine-grained shade patterns, especi
arXiv:2605.20763v1 Announce Type: new Abstract: Rapid progress in aerodynamic shape optimization (ASO) has outpaced currently-available standardized evaluation frameworks. Fair comparison requires a u
arXiv:2602.06358v2 Announce Type: replace Abstract: We propose SHINE (Scalable Hyper In-context NEtwork), a scalable hypernetwork that can map diverse meaningful contexts into high-quality LoRA adapte
arXiv:2605.21147v1 Announce Type: cross Abstract: As the number of model parameters increases, parameter-efficient fine-tuning (PEFT) has become the go-to choice for tailoring pre-trained large langua
arXiv:2605.20189v1 Announce Type: cross Abstract: Despite the remarkable success of large language models (LLMs), they still face bottlenecks while deploying in dynamic, real-world settings with prima
arXiv:2605.05863v2 Announce Type: replace Abstract: Incorporating prior data into online reinforcement learning accelerates training but typically forces a difficult trade-off between high computation
arXiv:2605.21384v1 Announce Type: cross Abstract: As long-horizon coding agents produce more code than any developer can review, oversight collapses onto a single surface: the automated test suite. Re
arXiv:2605.20296v1 Announce Type: new Abstract: Fine-tuning a language model for a target task routinely degrades capabilities the training data never explicitly threatened. We study this phenomenon,
Spent Tuesday watching @Google I/O thinking about a question. If you build on @Android, what just changed for you? Short answer: your screen belongs to Gemini now. After this week, Google owns the AI,
Ivan Mehta / TechCrunch: Spotify Labs launches Studio, a NotebookLM-like desktop app to generate private, AI-powered podcasts, in research preview across 20+ markets — One of the common features for c
Ivan Mehta / TechCrunch: Spotify says it has 1M+ subscriptions to Audiobook+, which is on track for $100M in ARR, and unveils an ElevenLabs-powered audiobook self-publishing tool — Alongside tools for
arXiv:2605.20738v1 Announce Type: new Abstract: Remote sensing imagery typically arrives in the form of continuous data streams. Traditional detectors often forget previously learned categories when l
arXiv:2605.21333v1 Announce Type: new Abstract: Natively trained spiking language models struggle to combine Transformer-like language quality, stable multi-domain pre-training, and high activation sp
arXiv:2603.21033v2 Announce Type: replace-cross Abstract: Geotechnical site characterisation relies on sparse, heterogeneous borehole data, where uncertainty quantification and interpretability matter
arXiv:2605.20731v1 Announce Type: new Abstract: Text-to-image models produce graphic design at production scale, but their supervision comes from photo-style preference data with a single overall verd
arXiv:2605.21443v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly being explored for video game quality assurance, especially gameplay glitch detection. Most existing eval
arXiv:2605.20876v1 Announce Type: new Abstract: Terminal agents extend Large Language Models with the ability to execute tasks directly in command-line environments, but their progress is bottlenecked
arXiv:2605.21338v1 Announce Type: new Abstract: LLMs have demonstrated exceptional proficiency in a wide range of NLP tasks. However, a notable gap remains in practical data analysis scenarios, partic
arXiv:2605.21090v1 Announce Type: new Abstract: Recent advances in Multimodal Large Language Models (MLLMs) and diffusion-based generative models have substantially improved prompt-driven image editin
arXiv:2605.20279v1 Announce Type: cross Abstract: Generative artificial intelligence is rapidly transforming the supply side of training data: an increasing share of new tokens, images, and structured
Many of the world’s fastest-growing AI startups are choosing to build their future — and the world’s — on Google Cloud because of our complete and open AI stack. We embed AI into every layer of our ar
arXiv:2510.08482v3 Announce Type: replace-cross Abstract: Iconicity, the resemblance between linguistic form and meaning, is pervasive in signed languages, offering a natural testbed for visual ground
arXiv:2605.20544v1 Announce Type: cross Abstract: Vision-language models (VLMs) are used as high-level planners for embodied agents, translating natural language instructions and visual observations i
arXiv:2605.21253v1 Announce Type: cross Abstract: Compositional score-based approaches to simulation-based inference (SBI) approximate the posterior over a shared parameter given n independent observa
arXiv:2511.04520v4 Announce Type: replace Abstract: Video generation has achieved remarkable progress, with generated videos increasingly resembling real ones. However, the rapid advance in generation
arXiv:2605.20639v1 Announce Type: cross Abstract: Optimization problems constrained by high-dimensional, time-dependent partial differential equations require repeated forward and sensitivity solves,
arXiv:2605.21295v1 Announce Type: new Abstract: Longitudinal passive sensing enables continuous health prediction, yet models often fail under cross-dataset distribution shifts. Traditional ML overfit
arXiv:2605.20502v1 Announce Type: cross Abstract: We address out-of-distribution (OOD) detection across the full spectrum of distribution shifts -- global domain changes, semantic divergence, texture
TLMs: Tiny LLMs and Agents on Edge Devices with @cormacb https://www.youtube.com/watch?v=-TiET_K-E_g Function Gemma ships at 270 million parameters and runs nearly 2,000 tokens per second prefill on a
arXiv:2605.21242v1 Announce Type: new Abstract: As robot fleets become more heterogeneous, including humanoids, rovers, quadrupeds, and drones, selecting the right robot for a task becomes a core syst
Today we release a study on decoupling the benefits of subword tokenization for language model training, by simulating each suspected benefit one at a time inside a 1.7B byte-level pretraining pipelin
Token Maxxing, April 2026-May 2026, RIP 🪦 🦔Microsoft canceled its internal Claude Code licenses this week after token-based billing made the cost untenable, even for a company with effectively infinit
arXiv:2605.20963v1 Announce Type: new Abstract: The proliferation of unmanned aerial vehicles (UAVs) has created urgent demand for precise UAV monitoring. Existing RGB-based systems rely on spatial cu
arXiv:2410.04155v2 Announce Type: replace Abstract: How to defend large language models (LLMs) from generating toxic content is an important research area. Yet, most research focused on various model
arXiv:2605.20885v1 Announce Type: new Abstract: Precision oncology requires predicting which drugs will suppress a specific tumor from its molecular profile, but drug-blind sensitivity prediction has
arXiv:2605.20477v1 Announce Type: cross Abstract: Language agents can adapt from experience in interactive environments, but current reflection-based methods can only self-correct within a single task