Knowledge catalogue
arXiv:2608.08224v1 Announce Type: new Abstract: Reinforcement learning post-training unlocks complex reasoning in LLMs. Yet benchmark scores reveal only whether a model improved, not what changed insi
arXiv:2608.08868v1 Announce Type: new Abstract: Many modern AI systems analyze conversational traces to infer aspects of human interaction and state, implicitly assuming that such information is recov
arXiv:2608.08061v1 Announce Type: new Abstract: The key question in moral judgement is not simply whether someone chooses the 'right' answer, but how they decide what matters most when moral principle
arXiv:2608.09324v1 Announce Type: new Abstract: On unlabeled test data, reinforcement learning lacks a ground-truth reward; test-time RL methods derive one from the model's own roll-outs, rewarding th
arXiv:2608.07693v1 Announce Type: cross Abstract: Generative traffic video forecasting aims to synthesize long-horizon, temporally coherent future videos of traffic scenes from a short observation his
arXiv:2608.07838v1 Announce Type: new Abstract: Large language models (LLMs) have increasingly supported response generation grounded in user-provided knowledge spanning heterogeneous structures. Howe
arXiv:2608.09443v1 Announce Type: new Abstract: Large language model (LLM) agents can support medication review between clinical visits, but safe choices for older adults with multimorbidity depend on
arXiv:2604.03374v2 Announce Type: replace-cross Abstract: Creative problem-solving requires combining multiple cognitive abilities, including logical reasoning, lateral thinking, analogy-making, and c
arXiv:2608.07481v1 Announce Type: cross Abstract: This paper investigates whether one large language model can approximate the humor preferences of another in a controlled Cards Against Humanity-style
arXiv:2608.09766v1 Announce Type: cross Abstract: Multilingual translation benchmarks are typically sourced in English and translated into other languages, treating language pairs as the unit of evalu
arXiv:2608.08545v1 Announce Type: cross Abstract: Robust navigation policies for autonomous agents must generalize across continuously varying environmental conditions such as turn rates, obstacles, f
arXiv:2608.07545v1 Announce Type: cross Abstract: An LLM agent's capability depends not only on model weights but on its harness: prompts, tools, skills, and control flow. Self-improvement loops alrea
arXiv:2504.12742v2 Announce Type: replace Abstract: Decentralized Federated Learning (DFL) enables collaborative model training without relying on a central server. When local objectives are nonconvex
arXiv:2608.09900v1 Announce Type: new Abstract: Large language model evaluations typically focus on performance under nominal conditions, creating an illusion of capability where models comfortably wa
Link: https://arxiv.org/pdf/2604.27883 Hi, Most of use are familiar with the headache of training a neural network using gradient descent where the training error may go to zero but the test error may
Spent two nights getting deepseek-ai/DeepSeek-V4-Flash-0731 (284B MoE, 13B active, native FP4/FP8, 1M context) running production-grade on two DGX Sparks connected by one QSFP DAC cable. Everything —
Been benchmarking DSv4 Flash 0731 on a Flow Z13 (Ryzen AI MAX+ 395, Radeon 8060S / gfx1151, 128GB LPDDR5X) for the past week. Figured I'd share what actually works and what doesn't — there are a lot o
DeepSeek V4 Flash 0731 is now available to fine-tune on Together AI. Specialize it for coding, tool use, and your own domain with SFT or DPO, then deploy the fine-tuned model on Together AI for produc
I'm very happy with some Linux admin tasks I'm throwing at a locally running DeepSeek. My request was simple, check why 'samples' folder is taking more and more space on one of the machines on my LAN,
Claude apps gateway is a self-hosted governance layer between Claude Code and Claude Desktop and Amazon Bedrock or Claude Platform on AWS. This post presents a production reference deployment covering
arXiv:2608.08959v1 Announce Type: new Abstract: Gravimetry images subsurface density contrasts associated with geological structures, geothermal systems, and intrusive bodies. Recovering a three-dimen
arXiv:2509.16609v2 Announce Type: replace Abstract: Accurately assessing image complexity (IC) is essential for many vision tasks, yet existing approaches rely almost exclusively on visual features an
arXiv:2608.08977v1 Announce Type: cross Abstract: This work focuses on the impact and detection of clear contact lenses in the context of iris recognition. While the detection of cosmetic or patterned
arXiv:2608.07614v1 Announce Type: cross Abstract: Code generated by LLMs can violate a developer's implicit intentions when given an ambiguous prompt, yet standard benchmarks measure only whether code
arXiv:2608.09053v1 Announce Type: cross Abstract: Cardiologists interpret electrocardiograms by localizing waveform components, measuring rhythm and interval patterns, and translating these structured
arXiv:2608.09691v1 Announce Type: new Abstract: Labeled images of small objects hidden in vegetation are scarce, and detectors trained on them generalize poorly across sites. Rather than reusing label
arXiv:2608.08320v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used to drive embodied social agents, yet it remains unclear whether larger models improve user perception
arXiv:2511.02577v2 Announce Type: replace Abstract: Proximal Policy Optimization (PPO) is widely regarded as one of the most successful deep reinforcement learning algorithms, known for its robustness
arXiv:2608.08523v1 Announce Type: new Abstract: Multimodal embodied agents are increasingly required to solve long-horizon tasks by integrating visual observations, textual goals, and interaction hist
arXiv:2608.09752v1 Announce Type: new Abstract: Retinal fundus images frequently exhibit multiple co-occurring pathologies, yet standard deep learning classifiers apply static, identical computation t
arXiv:2608.08878v1 Announce Type: cross Abstract: Transformer-based large language models (LLMs) achieve strong performance across many tasks, but their Key-Value (KV) cache grows linearly with sequen
arXiv:2608.08029v1 Announce Type: cross Abstract: Khatri et al. (2026) [DOI: 10.1109/DSN-W70714.2026.00027] show that lightweight MLP probes on final-layer activations of a single 8B model (LLaMA-3.1-
arXiv:2608.07527v1 Announce Type: cross Abstract: Long-document understanding requires models to find and combine evidence across many pages, layouts, tables, figures, and charts. Existing retrieval-a
arXiv:2608.08407v1 Announce Type: cross Abstract: A bidder can quietly buy a stake in a company before making an offer for it. That stake, a toehold, is supposed to pay for itself twice: it makes the
arXiv:2608.08624v1 Announce Type: new Abstract: Domain generalization (DG) and neural network pruning are conventionally treated as distinct objectives, targeting out-of-distribution (OOD) robustness
arXiv:2608.09043v1 Announce Type: cross Abstract: Users of modern platforms repeatedly need summaries of recent dialogue, but the window rarely contains enough context to be interpreted on its own. We
arXiv:2608.09042v1 Announce Type: new Abstract: Large traveling salesman problem (TSP) instances require a solver to allocate limited computation while preserving the validity of its outputs. Existing
arXiv:2608.08085v1 Announce Type: cross Abstract: Code performance optimization is a vital aspect of modern software development, as it enables faster response times and reduced resource usage. These
arXiv:2508.21041v4 Announce Type: replace-cross Abstract: Atypical mitotic figures (AMFs) indicate abnormal cell division associated with poor prognosis. Their detection remains difficult due to low p
arXiv:2608.09388v1 Announce Type: new Abstract: Human-scene interaction is an active research topic with several industrial applications in virtual reality, gaming, robotics, and surveillance. Despite
arXiv:2608.08322v1 Announce Type: cross Abstract: Physics-informed neural networks applied to the level-set formulation of interface advection commonly augment the residual and initial-condition losse
arXiv:2608.09548v1 Announce Type: cross Abstract: Large language models are increasingly deployed in education as tutors, teaching assistants, and content generators. These roles place demands that or
arXiv:2608.09024v1 Announce Type: new Abstract: Emergency-department (ED) triage requires clinicians to rapidly identify patients who need immediate attention, determine who can safely wait, and prior
arXiv:2608.09189v1 Announce Type: new Abstract: Despite significant advances in instruction-following and auditory comprehension, the evaluation of Emotional Intelligence (EI) in Spoken Language Model
arXiv:2608.08949v1 Announce Type: new Abstract: Dense 3D reconstruction is critical for clinical endoscopic navigation and documentation. While Gaussian Splatting SLAM systems show promise in this dom
arXiv:2608.08691v1 Announce Type: new Abstract: Residential virtual power plants (VPPs) can provide grid flexibility by shifting household demand, but physical flexibility becomes dependable capacity
arXiv:2608.09273v1 Announce Type: new Abstract: LLMs have demonstrated strong capabilities in code generation and automated program repair, but migrating an entire repository rarely produces a runnabl
arXiv:2608.09692v1 Announce Type: cross Abstract: Many of the series that generative time-series models are benchmarked on place a large probability mass on a single value --- it does not rain, no rid
arXiv:2608.09096v1 Announce Type: new Abstract: Large Language Models (LLMs) have driven rapid progress in autonomous agents, yet standard evaluations remain confined to static task solving. An emergi
arXiv:2608.07933v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) improves the factuality of large language models with external knowledge, yet conflicting evidence remains a fund
arXiv:2608.07552v1 Announce Type: cross Abstract: Semigroups of holomorphic self-maps of the unit disc with an interior fixed point are, by the classical Berkson--Porta representation, entirely determ
arXiv:2601.07565v2 Announce Type: replace-cross Abstract: Multimodal emotion understanding requires the integration of heterogeneous data sources, including text, audio, and visual modalities, while s
ExtractBench is one of the most comprehensive benchmarks for real-world document extraction. ✅ It covers 4869 pages, across 67 document types, spanning 8 real-world domains: finance, energy, gov, auto
arXiv:2608.08365v1 Announce Type: cross Abstract: Data-driven health-state estimators for SiC (Silica-Carbide) power modules typically report their performance on a single accelerated-aging campaign,
arXiv:2608.08284v1 Announce Type: new Abstract: Fairness audits for LLM-based recommenders have largely focused on observable outputs, implicitly assuming that stable recommendations reflect stable in
arXiv:2608.09474v1 Announce Type: new Abstract: Text-based person anomaly search requires retrieving real-world pedestrian images from detailed natural-language descriptions using models trained prima
arXiv:2511.18852v2 Announce Type: replace Abstract: Content moderation filters are a critical safeguard against alignment failures in language models. Yet most existing filters focus narrowly on gener
arXiv:2608.09250v1 Announce Type: new Abstract: Federated learning (FL) must serve devices with varying computational capabilities. A fixed model cannot suit all devices, while training one model per
arXiv:2608.09208v1 Announce Type: cross Abstract: Decentralized intelligence systems with heterogeneous devices and limited coordination increasingly rely on decentralized federated learning (DFL). Ho
arXiv:2608.08244v1 Announce Type: new Abstract: General wearable foundation models are pretrained across broad sensor streams and populations, but are not designed around women's-health tasks. We intr