Knowledge catalogue
arXiv:2608.07935v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) adapts a language model by distilling guidance from a frozen teacher on trajectories sampled from the student. Its ef
arXiv:2608.07636v1 Announce Type: cross Abstract: Deep-OCR (DeepSeek-OCR) advances document recognition by treating the visual modality as an optical compression medium, enabling long-context OCR at l
arXiv:2608.08859v1 Announce Type: cross Abstract: Wireless Body Area Networks (WBANs) generate multivariate physiological time series that are highly nonstationary and must often be processed under st
arXiv:2608.08977v1 Announce Type: cross Abstract: This work focuses on the impact and detection of clear contact lenses in the context of iris recognition. While the detection of cosmetic or patterned
arXiv:2608.08878v1 Announce Type: cross Abstract: Transformer-based large language models (LLMs) achieve strong performance across many tasks, but their Key-Value (KV) cache grows linearly with sequen
arXiv:2608.09043v1 Announce Type: cross Abstract: Users of modern platforms repeatedly need summaries of recent dialogue, but the window rarely contains enough context to be interpreted on its own. We
arXiv:2608.09656v1 Announce Type: new Abstract: Visual query localization (VQL) aims to retrieve and re-localize a queried object in egocentric videos, yet remains challenging when object boundaries a
arXiv:2608.08021v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) should answer from concrete image evidence rather than language priors, dataset shortcuts, or irrelevant visual context.
arXiv:2511.18852v2 Announce Type: replace Abstract: Content moderation filters are a critical safeguard against alignment failures in language models. Yet most existing filters focus narrowly on gener
Everything started with the sudden death of my old ASRock J1900. While looking for the perfect ITX replacement, I stumbled upon the Chinese CW-NAS-ADLN-K motherboard, which looked perfect on paper: In
arXiv:2608.08467v1 Announce Type: new Abstract: The Model Context Protocol (MCP) standardizes how servers expose data and tools to Large Language Models (LLMs). A common server design embeds frequentl
LLMs still produce bugs, but those bugs are different than what they used to be. It’s less off-by-ones and more about system design, ui usability, missing broader context. Some kinds of coding has bee
arXiv:2608.08176v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) improves the reasoning abilities of LLMs by internalizing privileged context into model parameters through self-disti
arXiv:2512.20968v2 Announce Type: replace-cross Abstract: Distributed attention is essential for scaling large language models (LLMs) to long contexts, yet existing methods either have limited paralle
arXiv:2608.09119v1 Announce Type: new Abstract: We introduce Motif 3, a decoder-only Mixture-of-Experts language model with 314 billion total parameters and 13.2 billion activated per token. Each spar
arXiv:2608.08684v1 Announce Type: cross Abstract: Long-context LLM inference is bottlenecked by KV cache memory, yet distributing a limited cache budget across layers remains challenging. Existing met
arXiv:2608.09885v1 Announce Type: new Abstract: The safety of large language model (LLM) agents depends not only on model weights but also on the agent harness that manages context, memory, tools, per
arXiv:2608.09745v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) converts feedback into dense token-level supervision on trajectories generated by the policy to be optimized, provi
arXiv:2608.07862v1 Announce Type: new Abstract: Existing safety evaluation datasets for large language models (LLMs) predominantly focus on English and Western contexts, often overlooking the linguist
arXiv:2608.07528v1 Announce Type: new Abstract: Linear probes detect corrupted context in language models with near-perfect accuracy, yet this does not translate into reliable failure prediction. The
arXiv:2604.00715v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) improves language model (LM) performance by providing relevant context at test time for knowledge-intensi
arXiv:2608.08791v1 Announce Type: new Abstract: Diffusion language models use broad context to create text, suggesting they might handle input noise better than standard models. Testing reveals this i
llama : support multi-output backend sampling (#25532) Enable backend sampling with token speculation Clamp the mask sum before converting it into the sampled index Add a numeric context parameter dec
arXiv:2608.06811v1 Announce Type: cross Abstract: Resolving a real software issue with a large language model (LLM) agent is a long repair episode, often tens to hundreds of steps spanning exploration
arXiv:2608.06939v1 Announce Type: new Abstract: Adverse weather causes diverse and complex image degradations, severely compromising the reliability of computer vision systems. Existing all-in-one res
arXiv:2608.07006v1 Announce Type: new Abstract: Visual retrieval-augmented generation (RAG) commonly expands the retrieved evidence set to improve answer-page coverage, implicitly assuming that all av
arXiv:2608.07411v1 Announce Type: new Abstract: In the context of geodata, existing Large Language Models have often been studied in a homogeneous setting, which has considerably limited insights into
arXiv:2608.07057v1 Announce Type: new Abstract: Knife-enabled violence presents a major public safety challenge, and law enforcement agencies require scalable tools for catalogue-level knife identific
arXiv:2608.06424v1 Announce Type: cross Abstract: Speech recordings often contain missing, corrupted, or incorrect regions that must be reconstructed or modified without re-synthesizing the entire utt
I have a classic test for local LLM's. I asked for 8 ball pool game with only one HTML file and Muse Glimmer spend 21k Token(I m using full context so 128k) and only created a 220 lines of HTML and sa
arXiv:2608.07088v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) encode images as long visual token sequences, making prefilling and KV-cache storage expensive. Existing trai
arXiv:2608.06672v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) has become a robust architecture for grounding large language models (LLMs) in trusted knowledge. However, standard
arXiv:2608.06663v1 Announce Type: new Abstract: Frontier language models solve reasoning problems in a single forward pass that would have been research contributions years ago, yet fail at multi-hour
AI agentic Internet traffic will obviously VASTLY exceed human usage. Not a close call at all. Cloudflare’s forecast is accurate. For context, Global bandwidth is somewhere between 2-8 Pbps (2,000-8,0
Looking for V100 users to share your config and it's performance. GPU: Tesla V100 PCIE 32Gb Qwen3.6 27B Q4_K_M + Q8_0 MTP 128K context length Pi coding agent llama.cpp model preset: [*] spec-default =
arXiv:2608.06196v1 Announce Type: new Abstract: Agents backed by large skill libraries must decide which skills to load and in what order. Loading the entire library into context is expensive and prov
arXiv:2608.05834v1 Announce Type: new Abstract: In this technical report, I present a new method for guiding image generation in the context of Virtual- Try-On (VITON). The proposed method leverages n
arXiv:2608.05169v1 Announce Type: new Abstract: Long-form story generation requires models to preserve narrative consistency across extended contexts, yet existing prompting-based methods often accumu
arXiv:2602.23565v3 Announce Type: replace Abstract: In many economically relevant contexts where machine learning is deployed, multiple platforms obtain data from the same pool of users, each of whom
arXiv:2608.05780v1 Announce Type: new Abstract: Recent advancements in MLLM-based long-form video understanding have mitigated inference-time computational cost and limited context lengths by selectin
arXiv:2608.06122v1 Announce Type: cross Abstract: Inspired by recent evidence that transformer architectures benefit from Self-PreTraining (SPT) on long-context benchmarks, we investigate whether simi
arXiv:2608.06218v1 Announce Type: cross Abstract: We study Muon, a recently proposed matrix-aware optimization method, in the context of the Stiefel manifold. This manifold consists of matrices with o
arXiv:2608.05604v1 Announce Type: cross Abstract: Large Language Models (LLMs) increasingly act as agents whose procedural knowledge is stored in reusable skill packages and loaded at inference time.
arXiv:2608.06288v1 Announce Type: new Abstract: This work presents a novel attention-based framework for estimating the Individual Probability of Treatment Benefit (IPTB) in survival analysis contexts
arXiv:2608.05663v1 Announce Type: new Abstract: Real-time long-form avatar audio--video generation requires causal, continuous synthesis while maintaining audiovisual synchronization and visual consis
arXiv:2602.06052v4 Announce Type: replace-cross Abstract: Research in artificial intelligence is shifting from model innovations and benchmark scores towards problem definition and rigorous real-world
arXiv:2608.05074v1 Announce Type: new Abstract: Spatial mapping of lung adenocarcinoma (LUAD) growth patterns across whole slide images (WSIs) requires resolving architectural context at the region le
arXiv:2608.04454v1 Announce Type: new Abstract: Mixture-of-experts vision-language models (MoE-VLMs) increase model capacity with sparse expert activation, yet deployment requires storing the full exp
arXiv:2608.04390v1 Announce Type: new Abstract: Large language models (LLMs) perform table-centric prediction through in-context learning, making demonstration selection critical to performance. Exist
arXiv:2608.04457v1 Announce Type: cross Abstract: As 'AI Scientists' emerge to drive research via the Model Context Protocol (MCP), systems relying on ephemeral scripts will fail. The sheer scale of s
arXiv:2608.04968v1 Announce Type: new Abstract: The capabilities of an LLM agent depend not only on its model but on the harness: the executable program that constructs context, invokes tools, verifie
J'ai consacré beaucoup de temps à l'optimisation de DeepSeek-V4-Flash-0731 GGUF sur une seule RTX 3090. Mon exigence absolue pour chaque configuration était la suivante : Le modèle doit rester utilisa
arXiv:2604.01693v2 Announce Type: replace Abstract: Video object removal aims to erase target objects while reconstructing visually plausible and temporally coherent content. However, target objects o
arXiv:2608.04132v1 Announce Type: new Abstract: High-resolution images and long videos provide vision-language models with rich context for multimodal reasoning and fine-grained perception, but the re
arXiv:2608.04060v1 Announce Type: cross Abstract: Joint-embedding predictive architectures learn abstract states by predicting target embeddings from context embeddings, but their transition models ar
arXiv:2608.04591v1 Announce Type: cross Abstract: Large language models (LLMs) are often asked whether something is absent from a record, list, or retrieved context. Yet non-observation licenses a neg
arXiv:2608.02876v1 Announce Type: new Abstract: Tool-using agents do not merely consume observations: their actions determine what arrives next. In agentic text-to-SQL, a broad query can spend context
arXiv:2608.03532v1 Announce Type: new Abstract: Large language models are increasingly deployed in multilingual contexts, yet safety alignment and bias evaluation remain overwhelmingly English-centric
arXiv:2608.03222v1 Announce Type: cross Abstract: Software engineering (SWE) agents resolve repository-level issues through long trajectories that grow increasingly expensive as context accumulates. F
Learn how LendingTree built a production multi-agent mortgage assistant on Amazon Bedrock. Three coordinated agents use LangGraph, the Model Context Protocol, and Amazon Nova models with built-in guar