Knowledge catalogue
arXiv:2609.23567v1 Announce Type: cross Abstract: We reconsider the theory of probabilistic formal languages generated by n-gram models and by probabilistic context-free grammars (PCFGs). The expected
arXiv:2609.22225v1 Announce Type: new Abstract: Large language models (LLMs) exhibit a range of human-like decision-making behaviors, but whether these reflect similar underlying mechanisms or surface
arXiv:2609.24971v1 Announce Type: new Abstract: Agents today often take real-world actions that depend on long-term memory and context recall over time. However, most current memory benchmarks are bui
arXiv:2609.23414v1 Announce Type: new Abstract: Socially competent humanoid robots must communicate affect and intent through gesture as well as speech, yet open-ended interaction must become motion t
I've been running FreeToken on my 2x3090 box for a while and ended up maintaining a fork of it. Posting it in case it's useful to anyone else here. Quick context if you haven't used it: FreeToken is a
arXiv:2609.22362v1 Announce Type: new Abstract: Debates about whether artificial systems can feel are often forced between two unsatisfactory positions: behavioral equivalence is treated as sufficient
arXiv:2609.24026v1 Announce Type: new Abstract: In this paper, we investigate the limitations of fixed, hand-crafted connectors in hierarchical semantic representations for open-vocabulary object dete
arXiv:2609.24259v1 Announce Type: new Abstract: The effectiveness of agent memory ultimately depends on whether the underlying LLM gives each memory in context an appropriate degree of influence over
Some people here say MiMo-V2.6 is bad with tools and are going back to GLM-5.3-Flash. I spent today running MiMo-V2.6-Flash-RL as the backend for an agent harness, on 2× DGX Spark with vLLM, using the
arXiv:2609.24377v1 Announce Type: cross Abstract: We study latent-space watermarking through a pretrained generator using a prescribed latent-to-output stochastic mapping, called the renderer. A water
arXiv:2609.23769v1 Announce Type: new Abstract: The disambiguation of semantically similar statutory text across jurisdictions is a retrieval problem that existing methods do not solve. This inter-con
arXiv:2609.22167v1 Announce Type: new Abstract: Predicting reaction yield from molecular structure and reaction context can cut experimental trial-and-error and speed up condition screening in synthet
arXiv:2609.23432v1 Announce Type: new Abstract: Dynamic rope manipulation is highly sensitive to unknown object dynamics: the same robot motion can produce substantially different responses across rop
arXiv:2609.24972v1 Announce Type: cross Abstract: An LLM agent's capability is largely magnified by its harness, namely the prompts, control flow, tooling, memory, and context management surrounding t
arXiv:2606.13279v2 Announce Type: replace Abstract: In bimanual robotic manipulation, task-relevant visual information varies with the task stage and context, while the interaction of the two arms shi
arXiv:2609.22158v1 Announce Type: new Abstract: Key-value (KV) caching is essential for efficient autoregressive large language model (LLM) inference, but the cache grows linearly with context length,
Teradata Corp. is expanding its Tera artificial intelligence assistant with a context engine and execution system designed to help agents carry out data tasks across enterprise systems. Tera is an age
arXiv:2609.22214v1 Announce Type: new Abstract: Long multilingual conversational spoken question answering requires systems to balance long-range transcript semantics with sparse acoustic and speaker-
arXiv:2609.24885v1 Announce Type: new Abstract: When a language model answers from a curated corpus via graph-based retrieval, a large grounding uplift does not establish reasoning over the retrieved
arXiv:2609.21805v1 Announce Type: cross Abstract: Background: Just-in-time adaptive interventions (JITAIs) can use behavioral data to adapt support to changing contexts, but many rely on predefined ru
arXiv:2609.21997v1 Announce Type: cross Abstract: LLM agents in social simulation revise their opinions implicitly, in context: how open an agent is to persuasion can neither be specified nor verified
arXiv:2609.21694v1 Announce Type: cross Abstract: Context: We developed a probabilistic machine learning method with the aim of performing the O(10)-way classification of low- and high-resolution spec
Demand for AI infrastructure is at an all-time high. Global accelerator shortages mean engineering teams can rarely get all the compute they need from just one data center — capacity comes a cluster h
arXiv:2609.21683v1 Announce Type: new Abstract: Conversational speech depends on dialogue context and the listener's immediately preceding behavior. We propose ReACT-TTS, a two-stage framework that us
arXiv:2609.20831v1 Announce Type: new Abstract: We study when limiting what a language model can see improves learning. We compare standard CoT, the more general learner that reads the full trace, wit
arXiv:2609.21844v1 Announce Type: new Abstract: Long transcripts are costly inputs for downstream NLP systems and often contain irrelevant context. We study query-conditioned topic localization: predi
arXiv:2609.21827v1 Announce Type: new Abstract: Speculative decoding accelerates LLM inference by drafting multiple tokens in parallel, with tree-based methods further improving efficiency through hie
I've been thinking a lot about the idea of how a human mind is similar to a digital neural network. Seeing videos of the fruit fly brain scan, and the crazy things people have done with it probably co
arXiv:2609.21734v1 Announce Type: new Abstract: Designing effective Human-Robot Interaction in task-oriented settings requires carefully balancing user engagement with socially acceptable levels of ro
xAI's Grok 4.6 is now available in Amazon Bedrock: a frontier model for long-running agents, coding, and knowledge work, with a 500K token context window and four reasoning effort levels. It runs on b
Sharing my successful experience here. My setup: RTX 5060 Ti 16GB (x16 PCIe slot) RTX 3060 12GB (x4 PCIe slot) RAM: 32GB CPU: Ryzen 5 5600 OS: Linux So I have a total of 28GB. Average tk/s: 50, and th
I am trying to learn more about long-term memory and how people are handling that nowadays. Historically, I have used a mixture of paid cloud AI services (ChatGPT, Gemini, OpenRouter API) and my own l
Been integrating Jev into my custom harness. I couldn't be more excited about the results I am seeing. Most demos on my timeline are flashy but very basic. Notice they are all about some boring classi
TL;DR: I run a mismatched Tesla V100-PCIE pair—one 16 GB card and one 32 GB card, 48 GB total—in a Proxmox/LXC-based local-inference lab. The practical winner so far is a recent CUDA build of llama.cp
arXiv:2609.19519v1 Announce Type: new Abstract: Language-model agents are increasingly asked to carry out work spanning days or weeks, such as an operations remediation or a research programme. Such a
arXiv:2609.19842v1 Announce Type: new Abstract: Effective EEG decoding requires representations that preserve organization among channels, local waveform dynamics, and long-range temporal context. Exi
arXiv:2609.19805v1 Announce Type: new Abstract: Grapheme-to-phoneme (G2P) conversion turns raw text into its phonemic form and is an essential part of both text-to-speech (TTS) and automatic speech re
Kimi K3 from Moonshot AI is now available on Amazon Bedrock, giving you a powerful new open-weight option for coding and knowledge work. It offers native vision, a 1-million-token context window, and
arXiv:2609.19877v1 Announce Type: new Abstract: Efficient long-term conversational memory requires retrieving sufficient evidence without indiscriminately expanding the context presented to the langua
arXiv:2609.19183v1 Announce Type: cross Abstract: Whether human or large language model (LLM), an agent in a discussion reads only a few of the others' contributions, bounded by cognition, context, or
arXiv:2609.20181v1 Announce Type: new Abstract: Accurate skin lesion segmentation is crucial for reliable computer-aided dermatological diagnosis, yet existing convolutional and transformer-based mode
arXiv:2411.19304v2 Announce Type: replace-cross Abstract: Context: Machine Learning (ML) significantly impacts Software Engineering (SE), but studies mainly focus on practitioners, neglecting research
arXiv:2609.20565v1 Announce Type: new Abstract: Recent advancements in large language models have revolutionized the field of psychological counseling, especially in the context of Cognitive Behaviora
Super interesting work from Zoom and colleagues. If you maintain a hand-built coding harness, there are some great insights here. (bookmark it) They held the execution loop of a coding harness fixed a
arXiv:2609.19824v1 Announce Type: new Abstract: Language-guided navigation for terrestrial-aerial bimodal robots requires selecting routes and locomotion modes that match scene context and task intent
arXiv:2509.24368v3 Announce Type: replace-cross Abstract: We introduce the first watermark tailored for diffusion language models (DLMs), an emergent LLM paradigm able to generate tokens in arbitrary
arXiv:2609.20593v1 Announce Type: new Abstract: Word-in-Context (WiC) remains challenging for language models, despite recent progress on lexical-semantic tasks. We hypothesise that this difficulty ar
arXiv:2609.17865v1 Announce Type: new Abstract: Frontier models are often evaluated on how they respond to safety information once it is already in context. We study an earlier decision point: whether
arXiv:2609.17682v1 Announce Type: new Abstract: Humans efficiently learn new tasks by reusing a rich repertoire of motor skills across different goals and contexts. A similar strategy can also be used
arXiv:2609.18852v1 Announce Type: new Abstract: Longitudinal electronic health records (EHRs) capture years of patient history across notes, codes, labs, and procedures, and contain evidence needed to
just saw some benchmarks on the omlx website for the m5 ultra (don’t know how official they are but they seem reasonable): Link For Qwen 3.8 27B q4 it gets 50 tok/s th and 1800 tok/s pp at8k context a
Editor's note: Lucius AI, a tender-intelligence startup covering markets across five continents, runs its entire data platform on AlloyDB for PostgreSQL with a single operator. By migrating semantic s
Learn how to enforce defense-in-depth authorization for Model Context Protocol (MCP) tools on Amazon Quick. This walkthrough wires Microsoft Entra ID group and claims-based JWTs through an Amazon Bedr
arXiv:2609.19048v1 Announce Type: new Abstract: In the context of differentiated on-demand goods delivery services, this study proposes an integrated optimization method for automated guided vehicles
arXiv:2609.17847v1 Announce Type: new Abstract: Learning from human feedback has become a central paradigm for training modern AI systems, where models of human utility are used as reward models in po
arXiv:2606.09338v2 Announce Type: replace Abstract: Large Language Models fail at implicit multi-hop reasoning: a model answers 'When was X born?' and 'Who is Y's closest friend?' correctly but fails
arXiv:2609.19088v1 Announce Type: new Abstract: Large vision-language models have achieved remarkable progress in multi-modal understanding, yet their capabilities in educational settings remain insuf
arXiv:2602.15882v2 Announce Type: replace-cross Abstract: Robot manipulation uses temporal context to select actions and visual foresight to assess their consequences, yet dense representations of pas
arXiv:2609.18154v1 Announce Type: cross Abstract: We describe our system for LitTraceQA (GroundLM @ EMNLP 2026): given a research question, retrieve the relevant papers from a pool of 27,487, cite the
arXiv:2408.07702v2 Announce Type: cross Abstract: Schema linking is a crucial step in Text-to-SQL pipelines. Its goal is to retrieve the relevant tables and columns of a target database for a user's q