Knowledge catalogue
arXiv:2609.07784v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for everyday assistance, yet existing benchmarks only partially reflect the requests users naturally
mentria.ai is a browser inference engine I've been building solo, from scratch in WebGPU/WGSL. This week it crossed a milestone I had been chasing for a while: a 27B one-bit model answering at up to 3
arXiv:2609.08826v1 Announce Type: cross Abstract: When an external reference set (an anchor) is used to decompose an LLM-judge panel's error into a quality signal and a shared common-mode error, stand
arXiv:2609.07004v1 Announce Type: new Abstract: Accurate segmentation of pulmonary lesions is essential for effective clinical diagnosis and treatment strategies. Existing segmentation approaches ofte
arXiv:2609.07070v1 Announce Type: new Abstract: Spatio-temporal context has become increasingly crucial for visual tracking. However, most existing approaches extract spatio-temporal cues via discrete
arXiv:2609.05708v1 Announce Type: cross Abstract: Aggregating heterogeneous vision-language models (VLMs) can improve multimodal reasoning, but neither an individual model's confidence nor that of the
arXiv:2504.05161v2 Announce Type: replace-cross Abstract: Score estimation is the backbone of score-based generative models (SGMs), especially denoising diffusion probabilistic models (DDPMs). A key r
arXiv:2609.06004v1 Announce Type: new Abstract: Quantitative spatial reasoning in visual-language models (VLMs) aims to infer spatial distances and directional relationships among objects in 3D space
arXiv:2609.05864v1 Announce Type: new Abstract: Domain Generalized Semantic Segmentation (DGSS) is a challenging task, as vision models often rely on low-level appearance cues that change across domai
arXiv:2609.06051v1 Announce Type: new Abstract: The sensitivity of visual recognition models to changes in image scale is well established, yet the factors governing this sensitivity across heterogene
arXiv:2508.06990v2 Announce Type: replace Abstract: Semantic navigation requires an agent to navigate toward a specified target in an unseen environment. Employing an imaginative navigation strategy t
arXiv:2609.07915v1 Announce Type: new Abstract: Large vision models provide useful representations for remote-sensing segmentation but are often too expensive for deployment at the satellite or field
arXiv:2609.06396v1 Announce Type: new Abstract: Recursive self-improvement (RSI) lets a system improve the model-building machinery from its own failures, so every later model inherits the gain. Yet R
arXiv:2609.06080v1 Announce Type: new Abstract: Deeply phenotyped cohorts combine clinical, imaging, molecular, and wearable observations across timescales from seconds to years. This breadth can reve
arXiv:2609.07328v1 Announce Type: new Abstract: Local pedestrian-vehicle forecasting spans heterogeneous physical scales: pedestrians combine root locomotion with articulated motion, whereas vehicles
arXiv:2609.05658v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly being explored for automating SystemVerilog Assertion (SVA) generation, yet most evaluations report correc
arXiv:2609.08281v1 Announce Type: new Abstract: Object detectors have shown remarkable performance in various fields, among these medical imaging, surveillance, and autonomous driving. However, they a
arXiv:2609.07394v1 Announce Type: new Abstract: Anticipating whether a person will interact from one's own perspective is a highly intuitive task for humans, that relies on a combination of cues. We i
arXiv:2609.05596v1 Announce Type: new Abstract: Can interactive vision-and-language agents learn not just what to say but also extbf{extit{when}} to say it? Current language models rarely plan over wh
arXiv:2506.05626v3 Announce Type: replace Abstract: Real-world knowledge can take various forms, including structured, semi-structured, and unstructured data. Among these, Knowledge Graphs (KGs) are s
arXiv:2609.06245v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) perform strongly on general visual understanding tasks such as visual question answering, yet they often strugg
arXiv:2609.07525v1 Announce Type: new Abstract: Incomplete multi-view multi-label learning requires not only robust semantic aggregation from partially observed views, but also label-aware exploitatio
Encode‑Prefill‑Decode (EPD) disaggregation is an inference optimization in NVIDIA Dynamo that separates vision encoding from LLM prefill–decode stages for multimodal requests. On image‑heavy prompts,
You don't need to be a command-line expert to run local AI. http://llama.app wraps the heavy lifting of llama.cpp into a clean UI, making it simple to deploy and manage models like Gemma 4. Instead of
arXiv:2609.04772v1 Announce Type: new Abstract: The high training cost of Graph Neural Networks (GNNs) has raised growing concerns regarding model ownership infringement, such as model stealing and un
arXiv:2609.05066v1 Announce Type: cross Abstract: As the scale of video surveillance data outpaces manual annotation capacities, weakly supervised video anomaly detection (WSVAD) has emerged as a crit
arXiv:2609.03693v1 Announce Type: cross Abstract: Large language models (LLMs) are vulnerable to jailbreak attacks that bypass safety alignment through carefully crafted prompts. Many existing defense
I wanted a quick calories counter for myself, using LLMs to evaluate the calories from pictures of meals + descriptions. I needed to pick a model so I made a quick benchmark. The setup was: - Nutritio
arXiv:2609.05318v1 Announce Type: new Abstract: Building on the pioneering paper of Kearns, Roth, and Ryu (SODA'26), we study information aggregation in a networked learning model. The model captures
arXiv:2609.05190v1 Announce Type: new Abstract: In this paper we illustrate a novel architecture generating interpretable behavior and explanations. We refer to this architecture as the Mirror Agent M
arXiv:2609.04861v1 Announce Type: new Abstract: Bidirectional discrete diffusion model appears naturally suited to genomic modeling because it can reconstruct missing sequence from both flanks. We dev
This comparison was requested by a few people, and certainly we were all eager to see the final results. The comparison had taken 11 days and the GPU was crunching numbers for ~167 hours. We've been c
src : add n_expert_used_max function (#28323) src : add n_expert_used_max function With Commit c61b98b ('model: add NVIDIA Nemotron-3-Puzzle-75B-A9B (NemotronHPuzzle) support (#25444)') it is now poss
arXiv:2609.03151v1 Announce Type: cross Abstract: Long-context reasoning for large language models (LLMs) is becoming increasingly important, but training over long sequences remains challenging due t
arXiv:2604.17125v2 Announce Type: replace-cross Abstract: The Model Context Protocol (MCP) widens the prompt injection attack surface of large language model applications to tool descriptions, paramet
arXiv:2609.04070v1 Announce Type: new Abstract: Bridging the gap between the discrete reasoning of Vision-Language Models and the continuous, physics-constrained nature of autonomous driving remains a
arXiv:2609.04083v1 Announce Type: cross Abstract: MLLM-based embedding models remain limited in compositional retrieval, often failing to distinguish scenes containing the same concepts but different
arXiv:2512.09108v2 Announce Type: replace-cross Abstract: Agentic AI systems built on large language models (LLMs) offer significant potential for automating complex workflows, from software developme
arXiv:2609.03966v1 Announce Type: new Abstract: Agent evaluations report a tool-call rate read off the serving stack. That number can be zero while the model is emitting well-formed calls: the interfa
arXiv:2609.03436v1 Announce Type: cross Abstract: Reasoning traces of large language models are widely read as containing 'breakthrough' moments and early-legible fates. Both readings rest on measurem
arXiv:2609.04194v1 Announce Type: new Abstract: Reasoning traces from chain-of-thought models appear to offer a legible window into how a model arrives at its answer. A growing body of work treats the
arXiv:2609.03213v1 Announce Type: new Abstract: Large language models (LLMs) exhibit in-context learning capabilities, where they can learn new tasks from prompt contexts without weight updates. We co
arXiv:2609.03527v1 Announce Type: new Abstract: Neonatal respiratory diseases are a major cause of neonatal morbidity and mortality, posing substantial challenges in clinical practice. Despite recent
When Google's Finance Engineering team needed to modernize their legacy data layer, they chose Spanner, a globally distributed, strongly consistent, multi-model database with high availability capabil
OpenAI’s new language‑model system **Astra** has achieved state‑of‑the‑art performance on three key workflow benchmarks: the Agents’ Last Exam, AutomationBench, and ScreenSpot Pro. These suites evalua
arXiv:2609.02101v1 Announce Type: cross Abstract: Federated learning (FL) lets institutions train a shared model without exchanging data, and Low-Rank Adaptation (LoRA) makes this practical at scale b
I want to share a short paper just published exploring a simple but surprisingly effective optimization for sparse MoE reasoning models. The idea: Instead of retraining anything, we just tweak the rou
arXiv:2505.21907v3 Announce Type: replace Abstract: AI copilots represent a new generation of AI-powered systems designed to assist users, particularly knowledge workers and developers, in complex, co
arXiv:2609.01962v1 Announce Type: new Abstract: Ultra-low-bit language models can reduce storage and memory bandwidth, but a nominal '1.58-bit' label does not fully describe the stored representation,
Upgraded my work LLM server from DSV4-Flash-0731 to the new Vision-Exp model and did this little test for fun to see quality comparison. Test was performed in Openweb UI connected to my vLLM container
arXiv:2603.03072v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used to assist scientists across diverse workflows. A key challenge is generating high-quality figures
arXiv:2609.00180v1 Announce Type: new Abstract: Large language models sometimes deceive users without being instructed to. However, much of the study on deception in models involves instructed decepti
arXiv:2609.01345v1 Announce Type: new Abstract: Inference cascades cut cost by answering most queries with a cheap model and escalating a hard tail to a frontier model that acts as verifier. A natural
arXiv:2601.06853v3 Announce Type: replace Abstract: Chain-of-Thought (CoT) prompting is widely adopted for mathematical problem solving, including in low-resource languages, yet its behavior under irr
arXiv:2609.00407v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models enable efficient scaling of large language model (LLM) inference but suffer from substantial data-movement overhead wh
arXiv:2606.23382v2 Announce Type: replace-cross Abstract: Transformer language models have become established tools for modeling human sentence processing, with measures such as surprisal and attentio
arXiv:2609.01274v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) improves language-model reasoning, but how these gains relate to inference-time decoding and searc
arXiv:2609.01437v1 Announce Type: cross Abstract: As agents move from research prototypes to deployed tools, their capability increasingly depends on model-external execution infrastructure, commonly
arXiv:2608.29632v1 Announce Type: cross Abstract: Competitive programming is increasingly being used to evaluate the algorithmic reasoning capabilities of large language models (LLMs). However, existi
arXiv:2609.00625v1 Announce Type: cross Abstract: Faithfully capturing diverse real-world objects with fuzzy, anisotropic structures, such as hair, fur, fibers, and textiles, for efficient real-time v