Knowledge catalogue
arXiv:2608.16843v1 Announce Type: new Abstract: Foundation models are increasingly used for perception, reasoning, planning, and action generation in embodied agents, creating security risks that can
arXiv:2510.03885v4 Announce Type: replace Abstract: In this paper, we demonstrate that mobile manipulation policies utilizing a 3D latent map achieve stronger spatial and temporal reasoning than polic
Overview UI-Mate-27B is an open-weight foundation GUI agent for long-horizon work across applications and operating systems. It observes live screenshots, reasons over the visible state, and produces
arXiv:2608.16806v1 Announce Type: cross Abstract: Large Language Models (LLMs) have demonstrated capabilities in in-context learning, task decomposition, step-by-step reasoning, and code generation, d
arXiv:2608.15085v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) exhibit substantial performance degradation in non-English visual reasoning, despite the strong multilingual co
Following up on my previous post about my budget server setup (Intel N100 + RTX 5060 Ti 16GB), a few of you asked for a deeper dive into my actual inference config and real-world agentic performance.
arXiv:2608.14016v1 Announce Type: cross Abstract: Live game commentary is scarce: it exists for professional esports broadcasts and almost nowhere else. We present a content-based video narration syst
arXiv:2603.21114v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) perform strongly on isolated spatial tasks, but whether their predictions remain persistent and mutually co
arXiv:2511.08001v3 Announce Type: replace Abstract: To facilitate effective, safe deployment in the real world, individual robots must reason about interactions with other agents, which often occur wi
Hi all! I finally just got around to testing out Qwen 3.8 27b. I'm using Unsloth's UD-Q8_K_XL quant as a sit-in replacement to Qwen 3.6 27b, same quant size. Wow -- this thing isn't messing around. I
arXiv:2608.14068v1 Announce Type: cross Abstract: Conversational recommendation for e-commerce is increasingly mediated by large language models (LLMs), yet many real-world deployments operate under a
arXiv:2606.12838v2 Announce Type: replace-cross Abstract: Predicting single-cell transcriptional responses to genetic, chemical and cytokine perturbations is a fundamental challenge in computational b
arXiv:2608.14089v1 Announce Type: new Abstract: Safety classifiers deployed with large language models often fail for two reasons: their decisions reflect the policy learned during training rather tha
arXiv:2608.13612v1 Announce Type: new Abstract: Natural-language interfaces to enterprise data must translate underspecified requests into governed, executable behavior while controlling invalid queri
arXiv:2608.13791v1 Announce Type: cross Abstract: Positron emission tomography (PET) imaging suffers from limited spatial resolution and low signal-to-noise ratio, which can compromise quantitative ac
arXiv:2608.14399v1 Announce Type: cross Abstract: Patients increasingly ask large language model (LLM) assistants which doctor to see, making these systems AI infomediaries: algorithms that intermedia
Title pretty much says it all. I’ve deployed Qwen 3.8 27B using vLLM on an RTX 6000 Pro (tried multiple vLLM releases and launch recipes), but I can't get it into a usable state because of crazy long
o3-mini (very obsolete) in an agentic loop made good exam questions: 'In one of the largest field studies of AI-generated questions to date, we found that this approach achieves psychometric propertie
model: add Kimi-K3 text model (#26185) model: add Kimi-K3 text model Hybrid KDA (linear) + MLA (full) attention as in Kimi-Linear-48B, plus five things that architecture does not have: cross-layer res
arXiv:2608.13160v1 Announce Type: cross Abstract: Multilingual retrieval-augmented generation (mRAG) equips large language models with access to globally distributed external knowledge for complex mul
arXiv:2608.12515v1 Announce Type: new Abstract: Assessing proxemic danger from a robot's egocentric perspective is critical for safe embodied navigation in human environments and requires both visual
arXiv:2608.12486v1 Announce Type: new Abstract: Large language models (LLMs) cannot retain post-deployment experience without parameter updates. We introduce DIVE, a diversity-driven framework that en
arXiv:2608.12343v1 Announce Type: new Abstract: AI chatbots are widely used by students as knowledge sources, yet LLM benchmarks rarely assess interpretative historical reasoning. We evaluate eight le
arXiv:2608.12336v1 Announce Type: cross Abstract: A story premise is the creative spark from which a full narrative can grow. Yet LLM-based story generation has mostly emphasized later-stage planning,
arXiv:2608.12875v1 Announce Type: new Abstract: Should you replace your text-embedding pipeline with a large language model? We answer this with a controlled, cost-aware comparison of ten LLMs across
arXiv:2608.13484v1 Announce Type: cross Abstract: When asked about entities outside their knowledge boundary, LLMs routinely fabricate plausible-sounding details rather than backing off to safer, more
arXiv:2408.06849v3 Announce Type: replace Abstract: The large language model (LLM) has achieved significant success across various domains. However, the inherent complexity of causal problems and caus
arXiv:2608.12187v1 Announce Type: cross Abstract: Transformer-based methods have achieved strong performance in monocular 3D human pose estimation, but most existing approaches organise spatial and te
arXiv:2608.11768v1 Announce Type: new Abstract: The adaptive neuro-fuzzy inference system (ANFIS) is an interpretable reasoning framework capable of generating explicit IF-THEN fuzzy rules, making it
arXiv:2608.11967v1 Announce Type: cross Abstract: Large language model agents increasingly rely on long-horizon reasoning to solve complex tasks involving planning, tool use, and memory. A critical ca
arXiv:2506.04571v3 Announce Type: replace Abstract: Agriculture is undergoing a major transformation driven by artificial intelligence (AI), machine learning, and knowledge representation technologies
arXiv:2607.11175v2 Announce Type: replace Abstract: The growing ability of large language models and vision-language models to jointly interpret and reason over images and text is reshaping medical im
arXiv:2602.24287v2 Announce Type: replace-cross Abstract: In multi-turn conversations, large language models typically condition on the full conversation history: both past user prompts and assistant
arXiv:2608.10628v1 Announce Type: cross Abstract: Long-document understanding often requires reasoning over many visually rich pages, making inference costly and prone to context rot. In this work, we
arXiv:2608.10057v1 Announce Type: new Abstract: We introduce LEGO for advanced open-vocabulary scene understanding. Beyond basic concept recognition, its core innovation lies in capturing the intrinsi
arXiv:2608.10537v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) have helped uncover mechanistic explanations for LLM behaviours such as reasoning, jailbreaking etc., via understanding the c
arXiv:2608.10504v1 Announce Type: new Abstract: As coding agents increasingly handle implementation, the central challenge shifts from building individual agents to building an infrastructure that sys
arXiv:2608.11191v1 Announce Type: cross Abstract: GUI Visual Grounding is a fundamental capability for GUI agents. Existing models typically freeze their parameters after deployment, limiting their ab
arXiv:2505.11635v2 Announce Type: cross Abstract: Many real-world tasks, from associative memory to symbolic reasoning, benefit from discrete, structured representations that standard continuous laten
arXiv:2608.10618v1 Announce Type: new Abstract: Embodied artificial intelligence aims to develop agents that perceive, reason, and act through continuous interaction with the physical world. However,
arXiv:2603.18446v2 Announce Type: replace Abstract: Long-context inference remains challenging for large language models due to attention dilution and out-of-distribution degradation. Context selectio
We are in an insane run of open-weight drops. Every modality, open source is winning. This is what an open source AI summer ☀️ looks like: 🧠 LLMs & Reasoning → DeepSeek-V4-Flash-0731 (my king 👑): 304B
arXiv:2608.08192v1 Announce Type: new Abstract: Standard approaches to abductive reasoning can retain multiple candidate explanations, but they do not generally combine explicit compositional cross-hy
arXiv:2607.10180v2 Announce Type: replace-cross Abstract: We introduce ActiveFly-Bench, the first benchmark to bridge cyberspace reasoning and physical-world interaction for UAV embodied perception. T
arXiv:2608.09217v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a central post-training paradigm for eliciting reasoning capabilities in large language models, yet uniform tas
arXiv:2602.11149v2 Announce Type: replace Abstract: Supervised fine-tuning (SFT) on chain-of-thought data is an essential post-training step for reasoning language models. Standard machine learning in
arXiv:2602.02704v2 Announce Type: replace Abstract: Reasoning over ultra-long documents requires synthesizing sparse evidence scattered across distant segments under strict memory constraints. While s
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:2603.28590v3 Announce Type: replace Abstract: Large language models (LLMs) can generate chains of thought (CoTs) that are not always causally responsible for their final outputs. When such a mis
arXiv:2608.07581v1 Announce Type: cross Abstract: Group-based reinforcement learning methods for multimodal large language models typically rely on trajectory-level credit assignment that applies a si
arXiv:2608.08726v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) uses a privileged teacher to supervise a reasoning model on prefixes sampled from its own rollouts. Yet each rollou
arXiv:2608.09772v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) have demonstrated strong performance on multimodal benchmarks, yet it remains unclear whether they genuinely reason
arXiv:2608.09044v1 Announce Type: new Abstract: Continual self-evolution requires LLM agents to transform environmental interactions into reliable and reusable experience. Existing methods typically r
Whoa, Meta released a new open-weight LLM yesterday, something that hasn't happened since the good old Llama days. Their Meta Muse Glimmer model is a 30B multimodal reasoning model with a Gemma-like a
Benchmarked Muse Glimmer 30B on my RTX 5090 (32GB), 262k context, UD-Q5_K_M + dflash-kquant + mmproj. Workload Stock master + DFlash ngram-simple PR #26842 + DFlash Code patch 78 t/s 57 t/s 220-253 t/
arXiv:2608.07202v1 Announce Type: new Abstract: Systematic reviews of Randomised Controlled Trials (RCTs) are routinely used as evidence for clinical care guidelines. Such evidence has to meet high re
arXiv:2608.06922v1 Announce Type: new Abstract: Negotiation is a demanding social task for LLM agents, requiring strategic reasoning, persuasion, and interpersonal adaptation. Yet existing benchmarks
arXiv:2608.06841v1 Announce Type: new Abstract: Object detection is a fundamental task in visual perception, providing structured region representations for recognition, grounding, reasoning, and inte
arXiv:2608.06614v1 Announce Type: cross Abstract: Large-taxonomy retrieval often assumes that the input already expresses the target concept. In many settings, however, the input is indirect evidence,
arXiv:2608.06434v1 Announce Type: cross Abstract: Embodied intelligence demands both long-horizon reasoning and real-time closed-loop responsiveness. Recent dual-system Vision-Language-Action (VLA) ar