Knowledge catalogue
This article discusses how prefix-aware routing and prefix caching techniques can reduce the computational overhead and costs associated with running large language models at scale by eliminating redu
arXiv:2601.19791v3 Announce Type: replace Abstract: We study grokking, the onset of generalization long after overfitting, in a classical ridge regression setting. We prove end-to-end grokking results
arXiv:2605.31069v1 Announce Type: cross Abstract: Accurately predicting future events is fundamental to content understanding and decision-making across various domains. While prior research has prima
arXiv:2505.18069v3 Announce Type: replace Abstract: Hebbian and anti-Hebbian plasticity are widely observed in the brain and are classically modeled as mechanistic, local homosynaptic rules stabilized
arXiv:2510.15710v3 Announce Type: replace Abstract: Medical workflows routinely combine reading images with producing visual and textual outputs, making both image understanding and generation central
arXiv:2506.01318v4 Announce Type: replace-cross Abstract: Machine unlearning (MU) aims to expunge a designated forget set from a trained model without costly retraining, yet the existing techniques ov
arXiv:2601.05770v3 Announce Type: replace-cross Abstract: Algorithm extraction aims to synthesize executable programs directly from models trained on algorithmic tasks, enabling de novo recovery of ex
arXiv:2605.30719v1 Announce Type: cross Abstract: We study when large language models (LLMs) can serve as effective black-box policy optimizers for reinforcement learning (RL) tasks, i.e., when can we
which is NOT new; see this quote from 5 years ago. the fact that all this is still true says a lot. This was right five years ago, and still is: “Large scale pretrained models are certainly likely to
arXiv:2605.30362v1 Announce Type: cross Abstract: Spiking neural networks (SNNs) hold promise for demonstrating superior learning and representation capabilities in deep models. Given the tremendous s
arXiv:2605.30833v1 Announce Type: cross Abstract: On-policy distillation transfers reasoning capabilities by training a student model on its own generated trajectories using token-level feedback from
Flux Identity Adjuster V2 is a ComfyUI node designed to improve identity consistency for FLUX.2 klein 9b models . It automatically throttles text strength when facial formation struggles, preventing c
This post likely argues that an individual's upbringing and early life experiences function similarly to a system prompt for an AI model—shaping foundational values, behaviors, and responses that infl
1/10 - PDF parsing at browser speed Jerry Liu showed LiteParse v2 using Rust to WebAssembly for sub-second extraction of messy PDFs, without calling a model. It can sit as a default step in agent and
B9434 is a release build identifier from the llama.cpp project, an open-source C/C++ implementation for large language model inference. Llama.cpp releases include updates, optimizations, and bug fixes
arXiv:2602.11171v2 Announce Type: replace-cross Abstract: Fine-tuning Large Language Models (LLMs) with Low-Rank Adaptation (LoRA) offers a resource-efficient way to personalize or specialize. However
arXiv:2605.30070v1 Announce Type: cross Abstract: Moving beyond simple scalar rewards toward richer world feedback is a natural path to more scalable RL post-training. On-policy self-distillation (OPS
arXiv:2605.29753v1 Announce Type: cross Abstract: Dual-energy CT (DECT) enables virtual monochromatic imaging (VMI) and improved contrast resolution, but its clinical adoption is limited by hardware c
arXiv:2603.01006v2 Announce Type: replace-cross Abstract: REPresentation Alignment (REPA) improves the training of generative flow models by aligning intermediate hidden states with pretrained teacher
This DigitalOcean blog post examines how emerging AI technologies are transforming business models and enabling startups to challenge traditional industries. It likely covers practical examples of AI-
arXiv:2605.29064v1 Announce Type: new Abstract: We study how persona prompting shapes language generated by multimodal large language models in an urban perception setting. Using 59,808 annotations fr
arXiv:2605.29139v1 Announce Type: cross Abstract: Federated Conformal RAG (FC-RAG) provides distribution-free coverage for a bandwidth-limited swarm of weak language models, but only at a fixed horizo
arXiv:2605.28829v1 Announce Type: cross Abstract: Competitive STEM examinations such as JEE and NEET require multi-step symbolic reasoning, precise numerical computation, and deep conceptual understan
B9393 is a build release of llama.cpp, the C/C++ inference framework for running large language models locally. llama.cpp enables LLM inference with minimal setup and state-of-the-art performance on a
b9401 is a release build of llama.cpp, an LLM inference framework in C/C++ that provides tools for running large language models locally. As an intermediate build in the llama.cpp project, it includes
B9402 is a release of llama.cpp, an open-source library that performs inference on large language models such as Llama and was developed in pure C/C++ with no dependencies. The release includes comman
arXiv:2605.29727v1 Announce Type: new Abstract: Block-diffusion drafters have recently emerged as a powerful alternative for speculative decoding by predicting multiple future-token distributions in a
arXiv:2605.29629v1 Announce Type: new Abstract: Attack Success Rate (ASR) evaluates each jailbreak with a single yes/no label at the end of generation, telling us whether a failure happened but not ho
arXiv:2605.30065v1 Announce Type: new Abstract: In this work, we focus on zero-shot 3D style transfer that can generate multi-view consistent stylized views of the 3D scene given an arbitrary style im
arXiv:2603.26668v2 Announce Type: replace-cross Abstract: As an important paradigm for enhancing the generation quality of Large Language Models (LLMs), retrieval-augmented generation (RAG) faces the
arXiv:2601.08064v2 Announce Type: replace Abstract: Confidence estimation (CE) indicates how reliable the answers of large language models are and impacts user trust and decision-making. Existing eval
arXiv:2603.01311v2 Announce Type: replace Abstract: The discovery of novel catalysts tailored for particular applications is a major challenge for the twenty-first century. Traditional methods for thi
arXiv:2605.29602v1 Announce Type: new Abstract: Multi-modal Retrieval-Augmented Generation (MMRAG) has emerged as a powerful paradigm for enhancing Multimodal Large Language Models in knowledge-intens
arXiv:2605.29628v1 Announce Type: cross Abstract: Contrastive Language-Audio Pretraining (CLAP) models are widely used for audio understanding and support modality-agnostic condition swapping in many
arXiv:2605.29612v1 Announce Type: cross Abstract: Although large language model (LLM) based multi-agent systems (MAS) show their capability to solve complex tasks and achieve higher performance over s
arXiv:2605.30085v1 Announce Type: new Abstract: Language model reasoning traces are rarely all-or-nothing; they frequently contain valid intermediate steps before a critical error occurs. Existing unc
arXiv:2605.28889v1 Announce Type: cross Abstract: Context distillation compresses contextual information into model parameters, yet existing methods often ignore how multiple distilled latent memories
arXiv:2505.02743v2 Announce Type: replace Abstract: Real-world data contains aleatoric uncertainty - irreducible noise arising from imperfect measurements or from incomplete knowledge about the data g
arXiv:2605.30133v1 Announce Type: new Abstract: We introduce CorPipe 26, our winning submission to the CRAC 2026 Shared Task on Multilingual Coreference Resolution. The fifth edition of this shared ta
arXiv:2410.07287v2 Announce Type: replace-cross Abstract: Climate change poses an existential threat, necessitating effective climate policies to enact impactful change. Decisions in this domain are i
arXiv:2605.29464v1 Announce Type: cross Abstract: In randomized trials involving multiple treatments, bivariate survival outcomes present significant analytical challenges for making decisions. This p
arXiv:2605.30039v1 Announce Type: new Abstract: Large Language Models have demonstrated remarkable progress in general-purpose capabilities and can achieve strong performance in specific domains throu
arXiv:2605.30200v1 Announce Type: new Abstract: The double-edged sword of integrating Large Language Models (LLMs) requires an effective triadic collaboration mechanism among LLMs, teachers and studen
arXiv:2605.29336v1 Announce Type: new Abstract: Improving the quality of model-generated summaries, especially factuality, the accuracy of a summary with respect to its source content, remains a chall
arXiv:2505.21876v2 Announce Type: replace-cross Abstract: Recent approaches for video generation with camera control often create anchor videos (i.e., rendered videos that approximate desired camera m
arXiv:2603.27667v2 Announce Type: replace-cross Abstract: Large Audio Language Models (LALMs) still struggle in complex acoustic scenes because they often fail to preserve task-relevant acoustic evide
arXiv:2605.30099v1 Announce Type: new Abstract: Valuable decisions and highly prioritized analysis now depend on applications such as facial biometrics, social media photo tagging, and human robots in
arXiv:2605.29161v1 Announce Type: cross Abstract: Generating realistic graph-structured data is challenging due to discrete connectivity, varying graph sizes, and class-specific structural patterns. R
arXiv:2605.29857v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for writing and review support, but their usefulness depends on context-dependent criteria, such as e
arXiv:2605.29937v1 Announce Type: cross Abstract: Diffusion models are effective for waypoint prediction in visual navigation, but standard sampling and test time guidance can produce unreliable or in
arXiv:2605.29461v1 Announce Type: new Abstract: LLM-conditioned segmentation has recently advanced rapidly by coupling large language models with iterative mask generation frameworks. However, we iden
Vercel updated its billing model to charge for serverless function invocations on a per-unit basis rather than previous pricing structures. This change affects how customers are charged for executing
arXiv:2605.29584v1 Announce Type: new Abstract: Reinforcement learning (RL) is a natural fit for agentic knowledge base question answering (KBQA), where a model must issue executable actions, observe
arXiv:2602.17200v2 Announce Type: replace Abstract: Despite high semantic alignment, modern text-to-image (T2I) generative models still struggle to synthesize diverse images from a given prompt. In th
arXiv:2605.30282v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have recently shown strong potential for robot learning by following language instructions. However, in practice, la
arXiv:2605.28888v1 Announce Type: cross Abstract: Real-world user behavior rarely consists of isolated actions; instead, it often forms intent flows governed by spatiotemporal dependencies. To provide
arXiv:2605.29980v1 Announce Type: cross Abstract: Multimodal alignment of histopathology encoders with transcriptomic and genomic data has been shown to significantly improve performance in downstream
arXiv:2605.29307v1 Announce Type: cross Abstract: Large Language Model (LLM) search agents have shown strong promise for knowledge-intensive language tasks through multiple rounds of reasoning and inf
arXiv:2605.29960v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly leverage long term memory to support persistent and autonomous task execution. However, this capability
arXiv:2605.28840v1 Announce Type: cross Abstract: Large language model (LLM) agents with tool-calling capabilities are increasingly deployed in production systems, yet a fundamental reliability questi