Knowledge catalogue
arXiv:2609.21212v1 Announce Type: cross Abstract: Learned navigation policies typically consume observations as a temporally ordered history, with positional encodings tying each observation to when i
I forked llama.cpp to implement Declarative Attention (arXiv:2609.02737, Google DeepMind and KAIST AI). The model declares in its own output which context chunks it needs <focus magic_chunks='N'>), an
Meet Qwen3.8-LiveTranslate, Qwen's next-generation real-time simultaneous interpretation model! 📢 Built on an Interleave architecture, it improves faithfulness, fluency, and conciseness while reducing
arXiv:2609.19768v1 Announce Type: new Abstract: Multivariate ocean forecasting must exploit shared evolution in a coupled ocean system while adapting to the heterogeneous statistical and dynamical cha
TypeSafe’s Jev classifies, scores, and routes without generating text — up to hundreds of times cheaper than an LLM judge. What that changes for evals, confidence routing, and application architecture
arXiv:2609.17534v1 Announce Type: new Abstract: Social desirability and impression management are pervasive sources of response distortion in human personality assessment, yet their effects on Large L
At Google, we see firsthand how the speed, scale, and sophistication of cyber threats continue to challenge traditional enterprise defenses. Today’s defenders can’t rely on reactive triage or fragment
arXiv:2609.18971v1 Announce Type: new Abstract: Surgical phase recognition maps each video frame to a clinically meaningful workflow phase, supporting context-aware assistance, documentation, and post
arXiv:2609.18844v1 Announce Type: new Abstract: Multimodal coding agents are expected to turn visual inputs into usable artifacts, and they act through a harness, the layer of tools, context managemen
arXiv:2609.17863v1 Announce Type: new Abstract: LLM inference optimizations report speedups on different models, GPUs, prompts, and quality metrics, making them hard to compare or combine. We build a
Apple paper: keep specs, schemas, tool config, and constraints; drop session traces. Selective shared memory beat both no memory and full history.
arXiv:2604.05012v2 Announce Type: replace-cross Abstract: Efficient inference with Large Language Models (LLMs) increasingly relies on Key-Value (KV) caches to store previously computed key and value
arXiv:2609.16730v1 Announce Type: new Abstract: Conversational memory changes during use, so endpoint question answering alone cannot establish how a persistent state accumulates, ages, or incorporate
arXiv:2609.14872v1 Announce Type: cross Abstract: Agentic serving can consume orders of magnitude more tokens than chatbot workloads, stressing both KV-cache capacity and decode-time bandwidth. Most K
arXiv:2504.01157v1 Announce Type: cross Abstract: Knowledge-intensive analytical applications retrieve context from both structured tabular data and unstructured, text-free documents for effective dec
arXiv:2609.15242v1 Announce Type: new Abstract: Environmental, Social, and Governance (ESG) reporting is critical for corporate accountability, with Large Language Models (LLMs) and Retrieval-Augmente
arXiv:2609.13778v1 Announce Type: cross Abstract: Human trajectory prediction requires modeling both individual motion patterns and social interactions among agents. Existing methods have made substan
After two days of fighting with benchmarking infrastructure, I finally benchmarked IFM/K2-Horizon-7B on 16GB VRAM. TL/DR: it works, but far behind Qwen-3.8-27B. Setup I compared 3 models - Qwen3.8-27B
arXiv:2609.15188v1 Announce Type: new Abstract: LLMs can generate fluent prose. Story quality depends on how decisions about plot, character, and language work together across planning, drafting, and
arXiv:2609.14507v1 Announce Type: cross Abstract: Single-GPU long-context inference with Mixture-of-Experts (MoE) models requires spilling the key-value cache (KVCache) to CPU memory. The spilled KV s
arXiv:2609.13251v1 Announce Type: new Abstract: Commercial and advertising images are frequently affected by poor framing, partially cropped subjects, truncated text or logos, and insufficient context
arXiv:2609.14691v1 Announce Type: cross Abstract: As autonomous vehicles and Extended Reality (XR) headsets enable novel in-car interactions, seamlessly querying physical landmarks, known as Outside-t
arXiv:2609.13956v1 Announce Type: new Abstract: In this report, we release Tabby, a long context probabilistic time series foundation model, together with a complete and open recipe of how it was buil
arXiv:2609.14991v1 Announce Type: new Abstract: Open Thai automatic speech recognition (ASR) is dominated by offline, Whisper-based models that read the whole utterance before transcribing, ruling out
arXiv:2609.12278v1 Announce Type: new Abstract: World models let agents plan by predicting the consequences of their actions, but changes in the environment can make them inaccurate. We study the prob
We are excited to share that Google Cloud was named a Leader and received the highest score in the ‘current offering’ category in the Forrester Wave™: Public Cloud Platforms, Q3 2026 report, which exa
Overview llama.cpp 0.4.1 adds Maple 20B-A1B, Tencent Hy 4, and Spark2.5 support, improves JSON schema handling, chat parsing, logging, and server child-process management, and updates ggml to v0.24.0.
arXiv:2609.11109v1 Announce Type: cross Abstract: The utility of AI in multi-coder qualitative coding has been widely discussed, yet little empirical evidence exists to delineate the contexts in which
arXiv:2603.28458v4 Announce Type: replace Abstract: Token-level sparse attention mechanisms, exemplified by DeepSeek Sparse Attention (DSA), achieve fine-grained key selection by scoring every histori
arXiv:2609.11561v1 Announce Type: new Abstract: Mainstream robotic policies often adopt a Markovian formulation, but many complex real-world manipulation tasks are inherently non-Markovian, requiring
arXiv:2609.09242v1 Announce Type: cross Abstract: Large Language Models (LLMs) often generate natural-language comments while writing code, and these comments become part of the context used to genera
arXiv:2609.08318v1 Announce Type: cross Abstract: The transition from human-centric assistance to Autonomous Software Engineering (ASE) agents has enabled the resolution of complex real-world SE tasks
arXiv:2602.13047v2 Announce Type: replace Abstract: Conversational speech reveals early signs of cognitive decline, including dementia and mild cognitive impairment (MCI). AI models show promise for s
arXiv:2609.08407v1 Announce Type: new Abstract: In this study, we identify depth-dependent prefix redundancy in final-readout LLM embedding models, notably across representative backbones including Qw
arXiv:2609.06634v1 Announce Type: cross Abstract: LLMs' performance on machine translation (MT) tasks is often dependent on the data availability in the specific domains and language pairs that they a
Github Repo. Blog post. 💡 TL;DR (from the Github Readme) Spend less without making the agent do less useful work. SoL-Pi is a standalone extension for Pi that packages four reusable efficiency mechani
arXiv:2609.09764v1 Announce Type: new Abstract: Social intelligence enables agents to read social context, infer intent, and adapt over sustained dialogue. As language models become autonomous collabo
arXiv:2609.07344v1 Announce Type: cross Abstract: Large language model (LLM) based agents are increasingly applied to cybersecurity tasks such as vulnerability discovery and automated penetration test
arXiv:2609.09233v1 Announce Type: cross Abstract: How can language model agents effectively leverage libraries of reusable knowledge to solve long-horizon tasks? Recent work has increasingly focused o
arXiv:2609.09840v1 Announce Type: new Abstract: Accurate long-term trajectory prediction for maritime vessels is essential for safety and logistical efficiency. While deep learning models, particularl
arXiv:2609.07568v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed for translation tasks, yet their implicit political positioning in such contexts remains unders
arXiv:2609.05882v1 Announce Type: cross Abstract: Multi-turn interaction creates a feedback process in which an LLM's previous responses become context for later behavior. Prior work shows substantial
arXiv:2609.05762v1 Announce Type: new Abstract: UAV image collections contain spatially and temporally related frames, yet semantic-segmentation benchmarks commonly split them at image level. Such spl
I have been a dwarfstar fan for awhile and I really liked glm 5.3 flash but needed it to be materially faster to feel good using it. In the screenshot you can see the outcome of using the model with a
arXiv:2504.15758v3 Announce Type: replace Abstract: We operate through the lens of ordinary differential equations and control theory to study the concept of observability in the context of neural sta
arXiv:2508.02184v3 Announce Type: replace Abstract: Ensuring truthfulness in large language models (LLMs) remains a critical challenge for reliable text generation. While supervised fine-tuning and re
arXiv:2609.07956v1 Announce Type: new Abstract: Tabular Foundation Models (TFMs) have recently demonstrated strong predictive performance through in-context learning, but their deployment in high-thro
arXiv:2602.13418v2 Announce Type: replace Abstract: Does natural language text have an intrinsic curvature? Language is increasingly modeled in curved geometries - hyperbolic spaces for hierarchy, mix
I’m currently running llama.cpp on two RTX 2060 12GB cards, so 24GB total VRAM. With Qwen3.8 27B IQ4_XS at 131k context I’m getting around 45 tok/s, which is actually pretty good for this setup. I fou
arXiv:2609.04647v1 Announce Type: new Abstract: Traditional Retrieval-Augmented Generation (RAG) systems score each passage independently against the query, assembling context sets that may be individ
arXiv:2609.04803v1 Announce Type: new Abstract: Pass receiver selection is a fundamental task in football analytics, aiming to predict the intended receiver under a given game state. This task is chal
Hi, I use hermes as a harness, and I am pleased with it, but sometimes Hermes's context size is a bit too much for my system, so I wanted to delegate or straight up use a lighter option for coding tas
DISCLAIMER I ramble a lot and am not good at focusing on documentation and or coherent thoughts. TLDR I did things I made a thing and it works for me. I will try to answer any questions. A few people
arXiv:2609.04384v1 Announce Type: cross Abstract: Chinese online comments often convey social meaning through indirect and playful language that is hard to interpret without context. Existing evaluati
https://huggingface.co/XHToken/Spark-X2.5-4B-GGUF https://huggingface.co/XHToken/Spark-X2.5-1.7B-GGUF from XHToken: We are introducing Spark-X2.5-4B and Spark-X2.5-1.7B, two compact, general-purpose l
Qwen3.8-Flash-Next (UD-Q4_K_XL) on a single RTX 3090 24GB + 128GB DDR4 — is this config optimal? Hardware CPU: Intel Core i5-12600K RAM: 128 GB DDR4 @ 3600 MHz GPU: NVIDIA RTX 3090, 24 GB VRAM OS: Win
Agentic-SDLC requires continuous learning 🎙️ New episode of The Agentic Review is live. @itamar_mar and @nnennahacks sit down with Emilie Schario, VP of Engineering at @anacondainc, to dive into AI RO
arXiv:2605.06508v2 Announce Type: replace-cross Abstract: Research artifacts are widely shared to support reproducibility, and artifact evaluation (AE) has become common at many leading conferences. H
Every answer in Perplexity starts with embedding and ranking models picking the most relevant results for the query. Today we published research on how we built SoTA serving infrastructure behind thos
We all want more tokens per second but I keep seeing confusion on what to expect for given hardware. For the decoding phase (TG/s) to produce one token all the model weights and KV cache needs to be r