Knowledge catalogue
arXiv:2506.24106v2 Announce Type: replace Abstract: We show that a language model's ability to predict text is tightly linked to the breadth of its embedding space: models that spread their contextual
arXiv:2604.16576v1 Announce Type: cross Abstract: Decoder-only large language models (LLMs) are increasingly replacing BERT-style architectures as the backbone for dense retrieval, achieving substanti
arXiv:2512.23405v4 Announce Type: replace Abstract: Blind inverse problems arise in many experimental settings where both the signal of interest and the forward operator are (partially) unknown. In th
arXiv:2509.23542v2 Announce Type: replace Abstract: The LLM-as-a-judge paradigm is widely used in both evaluating free-text model responses and reward modeling for model alignment and fine-tuning. Rec
arXiv:2510.05573v2 Announce Type: replace-cross Abstract: Continual learning, the ability of a model to adapt to an ongoing sequence of tasks without forgetting earlier ones, is a central goal of arti
arXiv:2601.18731v2 Announce Type: replace Abstract: Alignment of Large Language Models (LLMs) aims to align outputs with human preferences, and personalized alignment further adapts models to individu
one of my favorite quality of life features Claude Code in the terminal will now show recaps when you switch focus away from the session and then come back. This should help you stay more in flow whil
One of the most jarring things about current AI is its lack of introspection ability and metacognition. It doesn't know what it doesn't know, how it knows, or how it could find out. It's a one-way sys
arXiv:2604.18393v1 Announce Type: new Abstract: Diffusion models have achieved outstanding performance in unsupervised industrial anomaly detection (uIAD) by learning a manifold of normal data under t
arXiv:2604.17915v1 Announce Type: new Abstract: Vision-Language Models(VLMs) excel at autoregressive text generation, yet end-to-end autonomous driving requires multi-task learning with structured out
arXiv:2604.18486v1 Announce Type: cross Abstract: Chain-of-Thought (CoT) reasoning has become a powerful driver of trajectory prediction in VLA-based autonomous driving, yet its autoregressive nature
arXiv:2604.17984v1 Announce Type: new Abstract: Uncertainty quantification is crucial in safety-critical systems, where decisions must be made under uncertainty. In particular, we consider the problem
Only the fraud was stopped by DOGE and, even then, only some of the fraud On Friday, @StateDeptGHSD released its first wave of PEPFAR data, covering July-Sept 2025, after State took over USAID’s lifes
arXiv:2604.17512v1 Announce Type: new Abstract: Serialization formats designed for document interchange impose structural overhead that becomes prohibitive when large language models consume operation
open-source community will work their magic! If any inference providers could serve kimi k2.6 at 300+ tps reliably, I would be happy to switch from gpt 5.4 xhigh to kimi for daily tasks. It's a really
arXiv:2604.16957v1 Announce Type: new Abstract: We present Open-TQ-Metal, the first implementation of fused compressed-domain attention on Apple Silicon, enabling 128K-context inference for Llama 3.1
Digiday: OpenAI enables cost-per-click ads inside ChatGPT, setting bids at between 3 and 5 per click, in addition to CPMs — The platform that can figure out how to prove AI chatbots can drive an outco
OpenAI Group PBC today launched ChatGPT Images 2.0, an upgraded version of the image generator built into its popular chatbot. The company also debuted a new technical training service called Codex La
OpenAI's new Euphony tool works almost exactly the same way as my Codex transcript viewer https://tools.simonwillison.net/codex-timeline?url=https%3A%2F%2Fgist.githubusercontent.com%2Fsimonw%2Fa9eb599
OpenAI is rolling out the latest version of its AI-powered image generator with new 'thinking capabilities,' allowing it to search the web to help it create multiple images from a single prompt. On Tu
arXiv:2506.05606v5 Announce Type: replace Abstract: Can large language models (LLMs) accurately simulate the next web action of a specific user? While LLMs have shown promising capabilities in generat
arXiv:2604.16516v1 Announce Type: new Abstract: Text-to-Image (T2I) generation models have been widely adopted across various industries, yet are criticized for frequently exhibiting societal stereoty
arXiv:2604.17535v1 Announce Type: new Abstract: Extending the effective context length of large language models (LLMs) remains a central challenge for real-world applications. While recent post-traini
arXiv:2603.15528v2 Announce Type: replace Abstract: Underactuated robots are characterized by a larger number of degrees of freedom than actuators and if they are designed with a specific mass distrib
arXiv:2604.17802v1 Announce Type: cross Abstract: Generative Semantic Communication (GSC) is a promising solution for image transmission over narrow-band and high-noise channels. However, existing GSC
arXiv:2604.17135v1 Announce Type: new Abstract: Offline vectorized maps constitute critical infrastructure for high-precision autonomous driving and mapping services. Existing approaches rely predomin
arXiv:2510.02798v2 Announce Type: replace Abstract: Black-box optimization (BBO) underpins advances in domains such as AutoML and Materials Informatics, yet implementations of algorithms and benchmark
Venti iced coffee, light skim milk. That's what I get at Starbucks. It is what I have gotten at Starbucks every time I've been to Starbucks for as long as I can remember, other than a brief love affai
arXiv:2603.28584v2 Announce Type: replace Abstract: Optical Remote Sensing Image Salient Object Detection (ORSI-SOD) remains challenging due to complex backgrounds, low contrast, irregular object shap
Our core mission today is using AI to solve document OCR. All of our product offerings, from commercial (LlamaParse) to open-source (LiteParse, ParseBench), are fully aligned towards solving this prob
arXiv:2508.14461v3 Announce Type: replace Abstract: While multi-step diffusion models have advanced both forward and inverse rendering, existing approaches often treat these problems independently, le
arXiv:2604.18319v1 Announce Type: cross Abstract: Selection bias arises when the probability that an observation enters a dataset depends on variables related to the quantities of interest, leading to
arXiv:2511.21064v2 Announce Type: replace-cross Abstract: Open-Vocabulary Object Detection (OVOD) aims to enable detectors to generalize across categories by leveraging semantic information. Although
arXiv:2601.02986v2 Announce Type: replace Abstract: Recent approaches in personalized reward modeling have primarily focused on leveraging user interaction history to align model judgments with indivi
arXiv:2604.16554v1 Announce Type: new Abstract: Stroke patient cross-subject electroencephalography (EEG) decoding of motor imagery (MI) brain-computer interface (BCI) is essential for motor rehabilit
arXiv:2604.17219v1 Announce Type: cross Abstract: We derive explicit non-asymptotic PAC-Bayes generalization bounds for Gibbs posteriors, that is, data-dependent distributions over model parameters ob
arXiv:2510.07745v4 Announce Type: replace Abstract: Parallel test-time scaling (TTS) is a pivotal approach for enhancing large language models (LLMs), typically by sampling multiple token-based chains
arXiv:2604.18372v1 Announce Type: new Abstract: Parkinson's disease (PD) is a chronic neurodegenerative disease. It shows multiple motor symptoms such as tremor, bradykinesia, postural instability, fr
arXiv:2604.18327v1 Announce Type: cross Abstract: Reward models (RMs) are central to aligning large language models (LLMs) with human preferences, powering RLHF and advanced decoding strategies. While
ParseBench is the first benchmark to include VLM chart understanding 📊📈📉 over enterprise documents. 🟠 Existing benchmarks (ChartQA, ChartXiv) test over charts specifically and not the chart's inclusio
arXiv:2510.24235v3 Announce Type: replace Abstract: Reward models (RMs) are central to reinforcement learning from human feedback (RLHF), providing the critical supervision signals that align large la
arXiv:2604.17690v1 Announce Type: cross Abstract: Reconfigurable intelligent surfaces (RISs) modify signal reflections to enhance wireless communication capabilities. Classical RIS phase optimization
arXiv:2604.17570v1 Announce Type: new Abstract: Peripheral Blood Smear (PBS) is a critical microscopic examination in hematopathology that yields whole-slide imaging (WSI). Unlike solid tissue patholo
arXiv:2604.17831v1 Announce Type: new Abstract: Neural surface reconstruction methods typically treat camera poses as fixed values, assuming perfect accuracy from Structure-from-Motion (SfM) systems.
arXiv:2604.17819v1 Announce Type: new Abstract: Large language models (LLMs) perform substantially below human level on existing theory-of-mind (ToM) benchmarks, even when augmented with chain-of-thou
arXiv:2601.02933v3 Announce Type: replace Abstract: Human evaluation is the gold standard for multilingual NLP, but is often skipped in practice and substituted with automatic metrics because it is no
arXiv:2604.17667v1 Announce Type: new Abstract: Peer review is central to scientific publishing, yet reviewers frequently include claims that are subjective, rhetorical, or misaligned with the submitt
arXiv:2604.16515v1 Announce Type: new Abstract: The rapid proliferation of Multimodal Large Language Models (MLLMs) has enabled mobile agents to execute high-stakes financial transactions, but their a
The Space Force cancelled the Next Generation Operational Control System (OCX) contract, a troubled GPS ground control system program under prime contractor RTX , after spending $6.27 billion as of Ja
The Pentagon's 1.5 trillion fiscal 2027 budget proposal allocates nearly 54 billion for military drones and related technology, plus 21 billion for counter-drone weapons systems. At nearly 54 billion,
people compared GPT-5.4's solution of erdos #1196 to alphago's move 37 but i think a tighter analogy is to alphago's unusual (at the time) preferences for the 3-3 opening and early 3-3 invasion agains
arXiv:2602.04583v2 Announce Type: replace Abstract: Deep neural networks for visual perception are highly susceptible to domain shift, which poses a critical challenge for real-world deployment under
arXiv:2604.17863v1 Announce Type: new Abstract: Spinning flexible objects, exemplified by traditional Chinese handkerchief performances, demands periodic steady-state motions under nonlinear dynamics
arXiv:2604.08469v2 Announce Type: replace Abstract: Topological Data Analysis (TDA) provides tools to describe the shape of data, but integrating topological features into deep learning pipelines rema
arXiv:2604.16813v1 Announce Type: cross Abstract: Agentic AI systems are rapidly advancing toward real-world applications, yet their readiness in complex and personalized environments remains insuffic
arXiv:2505.17238v3 Announce Type: replace Abstract: Collaborative dialogue offers rich insights into students' learning and critical thinking, which is essential for personalizing pedagogical agent in
arXiv:2603.01332v2 Announce Type: replace Abstract: Multispectral demosaicing is crucial to reconstruct full-resolution spectral images from snapshot mosaiced measurements, enabling real-time imaging
arXiv:2604.17278v1 Announce Type: new Abstract: Effective pest recognition and management are crucial for sustainable agricultural development. However, collecting pest data in real scenarios is often
arXiv:2510.22048v3 Announce Type: replace Abstract: Power flow (PF) calculations are the backbone of real-time grid operations, across workflows such as contingency analysis (where repeated PF evaluat
arXiv:2604.17910v1 Announce Type: cross Abstract: Off-policy learning in constrained MDPs with large binary state spaces faces a fundamental tension: causal identification of transition dynamics requi