Knowledge catalogue
arXiv:2608.08115v1 Announce Type: new Abstract: Point cloud completion commonly follows a coarse-to-fine paradigm, where a low-density coarse shape is first predicted and then upsampled to the target
arXiv:2608.06557v1 Announce Type: cross Abstract: The reasoning and agentic capabilities of large language models have expanded the range of applications they support, from short interactive exchanges
The TileRT InferenceX article (Aug 10 2026) examines whether the TileRT software stack on NVIDIA GPUs can compete with dedicated inference systems such as Cerebras, Groq LPUs and SambaNova for ultra‑h
I discovered recently that Google uses their own TPUs, like tiny ASIC cards like the toy ones that existed for bitcoin. And while it sounds inefficient the fact they use thousands of them because...th
Press My earlier prediction that Tesla would buy them completely missed the mark. With AMD focusing heavily on the enterprise side, the idea of consumer-facing hot-swappable AI model chips looks prett
arXiv:2608.05303v1 Announce Type: cross Abstract: On-device deployment of Large Language Models (LLMs) has become essential for personalized edge applications. A primary bottleneck is external memory
arXiv:2608.06135v1 Announce Type: new Abstract: Large Language Models (LLMs) such as ChatGPT and Claude are widely used for information retrieval and problem-solving. Recent work has focused on improv
arXiv:2608.06085v1 Announce Type: new Abstract: Survey-country metadata can improve an LLM's forecast of an individual response when informative, yet the same cue may redirect the forecast when assign
arXiv:2608.02947v1 Announce Type: cross Abstract: The attention score with rotary position embeddings (RoPE) decomposes exactly into a sum over its 2D-rotation frequency pairs, and each pair's wavelen
arXiv:2608.02867v1 Announce Type: cross Abstract: Although reinforcement learning with verifiable rewards (RLVR) has improved the performance of large language models (LLMs) across a variety of reason
arXiv:2608.03388v1 Announce Type: new Abstract: Abductive reasoning requires forming hypotheses that explain observed evidence and revising them as new evidence becomes available. While large language
arXiv:2608.02633v1 Announce Type: new Abstract: Regional surveillance data reflect local transmission, reporting, seeding, and external infection pressure, which are difficult to identify separately.
arXiv:2608.03649v1 Announce Type: new Abstract: Fewer visual tokens do not guarantee lower end-to-end latency. We evaluate break-even with a reproducible protocol that accounts for decision overhead,
arXiv:2608.00701v1 Announce Type: cross Abstract: Reweighting source samples to match a target covariate distribution is a standard response to distribution shift when generalizing evidence from one p
arXiv:2608.00903v1 Announce Type: new Abstract: In animation production, paint-bucket colourisation for hand-drawn animation is a labour-intensive procedure that assigns each enclosed region in line s
arXiv:2603.27790v2 Announce Type: replace Abstract: We present a lightweight, training-free trajectory correction method that adapts a pretrained image editing model to each input manga image using on
arXiv:2607.28442v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) and vision-language models (VLMs) have enabled new possibilities for 3D question answering (3D-QA), a ke
arXiv:2607.26309v1 Announce Type: cross Abstract: Estimating causal effects of linguistic properties from observational text is difficult because the same document can contain both the treatment of in
arXiv:2607.26159v1 Announce Type: cross Abstract: An AI benchmark result rarely reaches a consequential claim in one step. Evaluators generalize it to further cases, interpret it as evidence of capabi
arXiv:2607.24981v1 Announce Type: new Abstract: Vision Transformer detectors now approach the accuracy of CNNs but remain difficult to deploy on NPUs and microcontrollers because key components, inclu
arXiv:2607.24788v1 Announce Type: new Abstract: As Large Language Models scale to increasingly long contexts, the memory I/O and computational overhead of the Key-Value (KV) cache during decoding emer
I work on PostSlate, a video editing tool, and this comes out of our own work. We run ML models on-device, face detection and embedding among other things, which means we can't assume anything about t
arXiv:2607.22761v1 Announce Type: cross Abstract: Resolving Design Rule Violations (DRVs) in layouts entails an iterative loop of geometric edits and verification. We present DRC-Aid, a closed-loop ag
arXiv:2607.20451v1 Announce Type: new Abstract: Semantic Field Theory (SFT) has developed from a philosophical critique of strong anti-formalist readings of language games into a proposed computationa
arXiv:2501.18897v4 Announce Type: replace-cross Abstract: Generative models have achieved remarkable success across a range of applications, yet their evaluation still lacks principled uncertainty qua
arXiv:2302.06578v4 Announce Type: replace-cross Abstract: We provide uniform confidence bands for kernel ridge regression (KRR), a widely used nonparametric regression estimator for nonstandard data s
arXiv:2607.16339v2 Announce Type: replace Abstract: Diffusion-based Large Language Models(DLLMs) enable parallel generation via Semi-Autoregressive (SAR) decoding in text generation. However, current
arXiv:2607.19864v1 Announce Type: cross Abstract: Diabetic retinopathy is a leading cause of preventable blindness; its early lesions are small, low contrast, and easily missed in manual screening. Mo
arXiv:2607.13080v1 Announce Type: cross Abstract: Autonomous coding agents force engineering organizations to choose between API-based frontier models -- strong reasoning at high token cost -- and on-
arXiv:2607.13428v1 Announce Type: new Abstract: Positive-Unlabeled (PU) learning aims to achieve high-accuracy binary classification with limited labeled positive examples and numerous unlabeled ones.
arXiv:2607.12726v1 Announce Type: cross Abstract: Global fits in high energy physics and cosmology often face the challenge of exploring high-dimensional parameter spaces with computationally expensiv
arXiv:2603.02204v2 Announce Type: replace Abstract: Selective conformal prediction can yield substantially tighter uncertainty sets when we can identify calibration examples that are exchangeable with
arXiv:2607.05708v1 Announce Type: new Abstract: Recent LLM-based agent systems continuously accumulate context across multi-turn interactions, tool invocations, and cross-session workflows. Replaying
arXiv:2607.05306v1 Announce Type: new Abstract: Integrating complex, multi-omics data presents significant challenges. Existing approaches often face a trade-off between model interpretability and rep
arXiv:2607.03333v1 Announce Type: cross Abstract: LLM agents are becoming a common interface for research, coding, and question answering, yet their Thought-Action-Observation loop is often serial: th
arXiv:2607.02521v1 Announce Type: cross Abstract: SwiGLU is the dominant MLP activation in modern large language models, yet its intermediate tensor materialization costs 9-37% of MLP execution time.
arXiv:2607.01814v1 Announce Type: new Abstract: Traditional Chinese Medicine (TCM) diagnosis, particularly through tongue inspection, faces persistent challenges in subjectivity and reproducibility. T
arXiv:2509.24421v5 Announce Type: replace Abstract: 3D Gaussian Splatting (3DGS) has emerged as an efficient approach for achieving photorealistic rendering. Recent MLP-based variants further improve
arXiv:2606.31804v1 Announce Type: new Abstract: Accurate energy demand forecasting is essential for the reliable operation and planning of modern sustainable energy systems. Spatial-temporal graph neu
arXiv:2606.31145v1 Announce Type: new Abstract: Large language models increasingly operate over long contexts, where the KV cache becomes a dominant memory bottleneck: its size grows linearly with seq
arXiv:2606.28932v1 Announce Type: cross Abstract: Large language models have driven recent progress in language and multimodal AI, yet pre-training them at scale is prohibitively expensive. Low-rank p
As organizations move from AI pilots to production AI factories, infrastructure decisions have shifted from peak chip specifications to cost per token: how many useful tokens they can deliver per doll
arXiv:2505.19809v3 Announce Type: replace-cross Abstract: In many real-world applications of regression, conditional probability estimation, and uncertainty quantification, exploiting symmetries roote
arXiv:2602.20610v3 Announce Type: replace-cross Abstract: Specifications are vital for ensuring program correctness, yet writing them manually remains challenging and time-intensive. Recent large lang
arXiv:2606.27550v1 Announce Type: new Abstract: Multi-token prediction has been shown to increase data density during training, improve downstream text-generation quality, and serves as the defacto ap
arXiv:2606.26105v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit strong capabilities in short-context reasoning but degrade in performance over long conversational horizons due t
arXiv:2606.26366v1 Announce Type: new Abstract: Standard chain-of-thought on moral dilemmas exhibits two failure modes: stakeholder collapse (the trace names at most one party with a stake in the outc
arXiv:2606.27161v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have achieved strong multimodal reasoning capabilities, but their efficiency is limited by the large number of
arXiv:2606.17165v3 Announce Type: replace-cross Abstract: Organizations and researchers show increasing interest in using large language models (LLMs) in place of human participants in A/B tests, in t
arXiv:2602.12542v2 Announce Type: replace-cross Abstract: Deep learning models for clinical event prediction on electronic health records (EHR) often suffer performance degradation when deployed under
arXiv:2606.09916v1 Announce Type: cross Abstract: Multi-turn LLM agents fan short queries into long trajectories of tool calls, search results, and intermediate reasoning. Both KV memory and KV read b
arXiv:2606.11151v1 Announce Type: new Abstract: Assistive mobility and manipulation platforms have received increasing attention as a means of restoring independence to individuals with disabilities.
arXiv:2606.10537v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) re-encode the entire prefix at every denoising step, causing recomputation that scales quadratically with contex
arXiv:2606.10445v1 Announce Type: cross Abstract: Semi-structured 2:4 sparsity is widely supported by modern accelerators, providing up to a 2x theoretical speedup. However, its strict 50% sparsity co
arXiv:2606.08761v1 Announce Type: cross Abstract: W4A4 quantization promises full utilization of INT4 Tensor Cores, yet group dequantization overhead on CUDA Cores has driven existing systems to mixed
arXiv:2606.05981v1 Announce Type: new Abstract: Aggressive distillation of the diffusion U-Net inverts the per-frame bottleneck of real-time text-to-image pipelines: once the denoiser is a 4-step or 1
arXiv:2606.04594v1 Announce Type: cross Abstract: LLM serving frameworks are quickly evolving with a complex software stack and a vast number of optimizations. The rapid development process can introd
arXiv:2606.04101v1 Announce Type: cross Abstract: Large-scale expert parallelism (EP) is becoming pivotal for training and serving frontier MoE models, but it also amplifies device-level expert load i
arXiv:2606.04286v1 Announce Type: new Abstract: Online reviews provide valuable insights into the perceived quality of facets of a product or service. While aspect-based sentiment analysis has focused
arXiv:2606.03014v1 Announce Type: new Abstract: Mixture-of-Agents (MoA) systems improve reasoning accuracy by routing each query to multiple expert LLMs and aggregating their outputs. Efficiently exec