Knowledge catalogue
arXiv:2608.29607v1 Announce Type: new Abstract: Mobile AI acts as a visual oracle, empowering users to snap a picture of something and ask for information. Snap-and-ask retrieval is now one of the mos
arXiv:2608.28694v1 Announce Type: new Abstract: Long-horizon video generation is evaluated with whole-frame metrics that reward motion and temporal consistency. For fixed-camera nature scenes this cre
arXiv:2608.30716v1 Announce Type: new Abstract: Recent advances in Large Multimodal Models (LMMs) have greatly improved video understanding, yet their ability to reason about human-centered social sit
Erin Woo / Wall Street Journal: Sources: Google plans to release Gemini 3.8 Flash as soon as Wednesday; Gemini 4 has done well on pre-training evals but still needs to complete post-training — Interna
arXiv:2509.18123v2 Announce Type: replace Abstract: Accurate interpretation of soil moisture patterns is critical for irrigation scheduling and crop management, yet existing approaches for soil moistu
arXiv:2608.29489v1 Announce Type: cross Abstract: Visual environmental risk recognition plays an important role in secure authentication, where a user's surroundings may reveal sensitive information o
arXiv:2512.02337v2 Announce Type: replace Abstract: Growing demands from tasks like code generation, deep reasoning, and long-document understanding have made long-context generation a crucial capabil
arXiv:2608.29069v1 Announce Type: cross Abstract: Operator-learning surrogates have been benchmarked largely on single-field, single-interface problems, leaving unclear whether architectural choices v
arXiv:2512.16956v3 Announce Type: replace-cross Abstract: Retrieving code functions, classes or files relevant to a user query, bug report or feature request from large codebases is a fundamental chal
arXiv:2608.29038v1 Announce Type: new Abstract: Noise poses a widespread challenge in signal processing, particularly when it comes to denoising images. Although convolutional neural networks (CNNs) h
arXiv:2601.16753v2 Announce Type: replace-cross Abstract: Longitudinal information in radiology reports refers to the sequential tracking of findings across multiple examinations over time, which is c
arXiv:2608.30987v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) trains a base language model to imitate target responses, and these targets may require knowledge the base model has not
arXiv:2608.31108v1 Announce Type: new Abstract: Efficient evaluation changes the protocol used to support claims about model behavior, yet it is rarely tested whether those claims remain stable after
arXiv:2608.30252v1 Announce Type: new Abstract: Long-context LLM applications such as document summarization and multi-turn agents require generation from prefixes spanning tens of thousands of tokens
arXiv:2608.29817v1 Announce Type: new Abstract: Neural Architecture Search (NAS) has so far rarely been applied to Mixture-of-Experts (MoE) models, and existing MoE designs leave the alignment between
arXiv:2608.29582v1 Announce Type: cross Abstract: Current evaluations of large language models (LLMs) primarily focus on factual knowledge retrieval, overlooking the fundamental challenge of navigatin
arXiv:2608.30872v1 Announce Type: new Abstract: Objective assessment of surgical technical skill is important for surgical training and structured feedback, but current workflows remain dependent on l
arXiv:2608.29992v1 Announce Type: new Abstract: This paper presents an end-to-end, agent-driven pipeline for the LoD3 reconstruction of facade openings in 3D city models, producing directly usable Cit
arXiv:2608.30661v1 Announce Type: new Abstract: Large language model-based multi-agent systems are evolving from fixed interaction topologies toward dynamically orchestrated Agent Swarms. However, exi
arXiv:2608.29935v1 Announce Type: new Abstract: Simulation of admittance-type models requires physically consistent dynamic models that are rarely available for off-the-shelf, everyday objects, limiti
arXiv:2603.22341v2 Announce Type: replace-cross Abstract: While prior red-teaming efforts have focused on eliciting harmful text outputs from large language models (LLMs), such approaches fail to capt
arXiv:2608.30068v1 Announce Type: new Abstract: Films communicate through deliberate creative choices, including lighting, color, composition, editing, dialogue, music, and sound. Humans naturally int
arXiv:2608.30745v1 Announce Type: new Abstract: The widespread adoption of encrypted traffic poses severe challenges to current security situational awareness systems based on network traffic monitori
arXiv:2608.29999v1 Announce Type: cross Abstract: Large audio-language models (LALMs) describe audio at the clip level but cannot assign timestamps to the events, speakers, or sounds they identify. De
arXiv:2608.30505v1 Announce Type: cross Abstract: Large language models (LLMs) are built from structured high-dimensional objects such as token representations, weights, adaptation updates, caches, an
arXiv:2608.28641v1 Announce Type: cross Abstract: Most evaluations for coding agents are conducted exclusively in English, which does not reflect real-world multilingual deployment. We present Termina
arXiv:2608.28660v1 Announce Type: cross Abstract: Test-time scaling (TTS) improves language model reasoning by allocating additional test-time compute, but prior work mainly studies closed-ended tasks
arXiv:2606.21803v2 Announce Type: replace Abstract: Next-token prediction is the self-supervised signal that trains language models, and every observed prompt token provides the same signal at test ti
arXiv:2608.31084v1 Announce Type: new Abstract: The Jacobian Lens (J-lens) is a recent tool for interpreting LLMs. It reads a hidden state as a ranked list of vocabulary tokens, leaving multi-token co
arXiv:2608.28859v1 Announce Type: cross Abstract: Reasoning models do not stop when they know the answer. On DeepSeek-R1-Distill-Qwen-7B the chain of thought runs about twice as long as the model's ow
arXiv:2608.29998v1 Announce Type: new Abstract: Planning-time intervention fidelity is a distinct, measurable property of a learned world model: whether the model's own open-loop transitions move task
arXiv:2608.28664v1 Announce Type: cross Abstract: Despite the success of foundation models in language and vision, their expansion into embodied AI is bottlenecked by a lack of generalized touch sensi
arXiv:2608.29843v1 Announce Type: cross Abstract: Posted prices for AI inference have fallen steadily since 2024, yet the measured speed of that fall depends almost entirely on the method of measureme
arXiv:2608.28595v1 Announce Type: new Abstract: Biomedical NLP pipelines routinely presuppose clean input text, yet large-scale corpora assembled through automated PDF parsing harbour pervasive OCR-li
There’s generally a massive difference in quality between specialized OCR providers, “simple” open-weight OCR models, and free/OSS solutions. 1️⃣ Specialized OCR models (including LlamaParse) solve fo
arXiv:2608.29093v1 Announce Type: new Abstract: We propose Titans-QFWP, a hybrid reinforcement learning architecture integrating a Quantum Fast Weight Programmer with Titans-style memory (Persistence,
arXiv:2608.29930v1 Announce Type: new Abstract: Black-box model attribution is increasingly relevant when large language models (LLMs) are served through relay and reseller APIs. A tempting low-cost s
arXiv:2608.31082v1 Announce Type: new Abstract: Valuable data remains embedded in unstructured sources: web pages, reports, contracts, filings, earnings calls, and PDFs. The big bet in enterprise AI i
arXiv:2608.28701v1 Announce Type: new Abstract: Diagram-to-graph topology extraction aims to extract a graph of entities and their connections from a structural diagram. This task remains challenging
arXiv:2608.30213v1 Announce Type: cross Abstract: Text recognition, or extracting electronic text from document images, has been indispensable for knowledge retrieval tasks, such as retrieval-augmente
arXiv:2608.29596v1 Announce Type: new Abstract: Autonomous large language model (LLM) agents increasingly face reliability, context consumption, and execution stability bottlenecks when deployed on co
arXiv:2508.14273v3 Announce Type: replace Abstract: As researchers increasingly adopt LLMs as writing assistants, generating high-quality research paper introductions remains both challenging and esse
arXiv:2603.04191v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly serving as personal assistants, where users may share individual preferences over extended interaction
arXiv:2608.30923v1 Announce Type: cross Abstract: Stream learning is commonly evaluated through predictive performance and adaptation to concept drift. However, sustained operation of a stream learner
arXiv:2608.30472v1 Announce Type: new Abstract: Molecular toxicity prediction is increasingly used to prioritise compounds before experimental testing, but conventional benchmark performance can overs
arXiv:2608.30720v1 Announce Type: new Abstract: Representational similarity is foundational to analyses of deep networks, yet distances between point-valued representations are not intrinsically tied
arXiv:2608.31117v1 Announce Type: cross Abstract: Generative models have become central across science and industry, from image and text synthesis to the design of molecules and materials. Quantum gen
Train past the frontier. @tryheidi's ambient scribe drafts a clinical note the clinician has to trust enough to sign. They fine-tuned open models on Fireworks whose notes their clinicians preferred ov
arXiv:2604.18364v2 Announce Type: replace Abstract: Generating programmatic animation using libraries such as Manim presents unique challenges for Large Language Models (LLMs), requiring spatial reaso
arXiv:2608.29160v1 Announce Type: cross Abstract: We aim to improve frozen flow-matching image generators by adding inference computation inside the denoiser, without changing model weights or the out
arXiv:2608.30769v1 Announce Type: new Abstract: LLM training is increasingly vulnerable to silent data corruption (SDC), yet existing protection methods largely treat Transformer computations uniforml
arXiv:2509.17930v3 Announce Type: replace-cross Abstract: Multilingual translation suffers from computational redundancy, especially when translating into multiple languages simultaneously. In additio
arXiv:2608.29577v1 Announce Type: new Abstract: Traditional video highlight detection relies on a narrow, event-centric definition of saliency, which often fails to generalize to unconstrained persona
arXiv:2608.30567v1 Announce Type: new Abstract: We present Turing-20B-A2B, a 20B-parameter Mixture-of-Experts language model that activates approximately 2B parameters per token, designed for long-con
arXiv:2508.20766v2 Announce Type: replace-cross Abstract: Safety alignment in Large Language Models (LLMs) often involves mediating internal representations to refuse harmful requests. Recent research
arXiv:2608.30688v1 Announce Type: new Abstract: While face recognition systems are widely deployed, ensuring their demographic reliability and robustness under uncontrolled visual conditions remains a
arXiv:2510.22588v2 Announce Type: replace-cross Abstract: Spoken dialogue models currently lack the ability for fine-grained speech style control, a critical capability for human-like interaction that
arXiv:2608.29235v1 Announce Type: new Abstract: Anti-UAV perception systems must remain reliable when sensor streams degrade under occlusion, fast motion, or modality-specific failure. Existing multim
arXiv:2608.29152v1 Announce Type: cross Abstract: We study the empirical Sinkhorn estimator of the entropic optimal transport potentials under the uniform loss. Since the potentials are only unique up
I posted a new gfx906 based llama.cpp fork a few days ago. One of the main points of critique was that i did not provide sufficient numbers for the gains to be achieved. -- TL;DR: After switching our