Knowledge catalogue
Prinz has been running legal benchmarks against AI systems and the latest models are very good... but cheaper/low reasoning models are not very good. So, how do you make sure your vendor selling an AI
arXiv:2608.30751v1 Announce Type: new Abstract: Large language models (LLMs) trained only on text and code can sometimes generate programs that draw recognizable images. However, it is unclear whether
arXiv:2608.29120v1 Announce Type: cross Abstract: Speech Language Models (SLMs) are increasingly deployed in multi-speaker environments, yet their ability to attribute speech to the correct speaker an
arXiv:2608.28666v1 Announce Type: new Abstract: Video-language models (VLMs) remain brittle on tasks that require tracking events over time and grounding answers in specific spatial regions. We propos
arXiv:2607.14252v2 Announce Type: replace-cross Abstract: Embodied agents accumulate experience over time. We study how accumulated experience can be formed into persistent memory for future reasoning
arXiv:2608.30451v1 Announce Type: new Abstract: Image-based 3D visual grounding is critical for embodied agents, yet existing benchmarks suffer from loose text-observation alignment and neglect tempor
The Information: Source: OpenAI's Astra model uses “recurrent depth”, a technique that improves cost and performance but obscures the AI's reasoning, making it harder to monitor — OpenAI says its fort
arXiv:2608.30924v1 Announce Type: new Abstract: Travel itinerary generation requires balancing strict spatio-temporal constraints with human preferences. Existing LLM-based planners mainly rely on str
arXiv:2608.27609v1 Announce Type: new Abstract: Vision-language-action models (VLAs) have shown strong promise for general-purpose robotic manipulation by mapping language instructions and vision obse
arXiv:2608.28270v1 Announce Type: new Abstract: We present a real-time semantic navigation framework for Unmanned Aerial Vehicles (UAVs) focused on improving time efficiency in the Object Goal Navigat
PSA: For everyone using GLM-5.3 you probably want to use this model in reasoning_effort='high' mode. > 'max' - 34% for 77k tokens (not bad!) > 'high' - 32% for 50k tokens But 'max' is not as unusable
arXiv:2608.27046v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) and other RL-style post-training paradigms have been used for aligning large language models (LL
arXiv:2608.25487v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) has emerged as a powerful architecture for Question Answering (QA) by integrating external information into Large L
arXiv:2608.23898v1 Announce Type: new Abstract: We introduce BenchBench-Protocol, a benchmark for large language models of 149 protocol-modification tasks recovered from modifications that scientists
arXiv:2607.08960v2 Announce Type: replace-cross Abstract: Warehouse operations are governed by Standard Operating Procedures (SOPs) that encode complex, multi-system decision logic, which must be exec
arXiv:2601.16520v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable progress in visual recognition and semantic understanding, yet precise compo
arXiv:2608.22885v1 Announce Type: new Abstract: Referring Expression Segmentation (RES) aims to generate a pixel-level mask for the object specified by a language expression. Recent methods based on m
arXiv:2506.18919v5 Announce Type: replace-cross Abstract: As a multimodal communication medium that integrates images and text, memes often convey implicit harmful content through metaphors, satire, a
arXiv:2608.21811v1 Announce Type: new Abstract: Reinforcement learning for vision-language math reasoning starves under sparse reward: on a pool of 20,830 visual-math problems where Qwen2-VL-2B answer
arXiv:2507.17448v2 Announce Type: replace-cross Abstract: Retrosynthetic planning is a cornerstone of organic synthesis and drug discovery. Yet existing AI methods often rely on pattern matching rathe
arXiv:2608.22857v1 Announce Type: new Abstract: Vision-language models (VLMs) frequently fail at visual change reasoning, even when their vision encoders contain sufficient information. We observe tha
arXiv:2608.22132v1 Announce Type: cross Abstract: Biomedical multi-hop question answering (QA) requires models to connect evidence across intermediate entities such as diseases, drugs, proteins, and p
arXiv:2608.22950v1 Announce Type: new Abstract: Floating waste in inland waterways threatens aquatic ecosystems and requires timely monitoring under cluttered, multi-object conditions. Existing aquati
arXiv:2608.20564v1 Announce Type: new Abstract: Multi-agent LLM systems can improve reasoning by pooling diverse perspectives, but their effectiveness depends on coordinating communication, particular
arXiv:2608.21022v1 Announce Type: new Abstract: Micro-actions are subtle, short, low-amplitude body movements, such as a fidgeting hand or a slight head tilt, that humans perform with little conscious
arXiv:2505.11821v3 Announce Type: replace Abstract: Reinforcement Learning (RL) approaches have been wildly used to enhance the reasoning capabilities of Large Language Model (LLM) agents in long-hori
I'm building a local AI companion and I'm currently working on its cognitive layer. The goal is: User message → understand intent → decide what context is relevant → retrieve only useful memories/stat
SemiAnalysis: With each successive era of AI, from early scaling, to reasoning, to agentic, open models have taken half as long to catch up to the first closed model — Comparing open vs. closed models
arXiv:2608.19380v1 Announce Type: new Abstract: While modern autonomous driving systems excel at perception tasks such as object detection and trajectory prediction, they lack the high-level causal re
arXiv:2608.19964v1 Announce Type: new Abstract: Autonomous driving systems must operate under partial observability, where safety-critical objects may be occluded or visible only to neighboring connec
HAHAHAHAHAHA non technical people are so incredibly cooked they are burnt thru can u imagine covering ai with zero context, zero reasoning, zero internal world model. it must be so delightfully joyful
I benchmarked Qwen3.8-27B on MathArena/aime_2026 dataset, comparing BF16 and FP8 weights at medium and xhigh reasoning effort. Interesting findings are: quantized FP8 xhigh is better than BF 16 medium
arXiv:2608.15788v1 Announce Type: new Abstract: Spatial intelligence requires foundation models to maintain coherent spatial state across interactions with the physical world. However, existing data-c
arXiv:2607.10139v3 Announce Type: replace-cross Abstract: Selecting the correct answer from a pool of candidate reasoning chains is the engine of test-time scaling, yet the standard selectors each car
arXiv:2608.14927v1 Announce Type: new Abstract: Multi-agent large language model (LLM) systems can improve reasoning by spending more computation, but deployment requires deciding when extra collabora
arXiv:2608.15445v1 Announce Type: new Abstract: When a reward is correct on every training example yet consistent with more than one goal, a model can acquire an unintended one, a failure known as goa
arXiv:2608.16709v1 Announce Type: cross Abstract: A radiologist reading a model's output faces two problems. The model returns a number and no reason, and any system that turns that number into readab
arXiv:2608.14741v1 Announce Type: cross Abstract: We introduce PolyComp, a procedurally generated and verified benchmark that stresses visual recognition and compositional spatial reasoning. In each p
arXiv:2608.14569v1 Announce Type: new Abstract: Neural solvers for constraint satisfaction problems have achieved remarkable in-distribution accuracy, yet they suffer from a fundamental limitation per
arXiv:2608.16480v1 Announce Type: cross Abstract: We present RISE (Roadside Infrastructure Sequence Understanding and Evaluation), a framework spanning metric 3D tracking and structured vision-languag
arXiv:2608.16742v1 Announce Type: cross Abstract: Large Language Models (LLMs) have achieved remarkable progress in code generation, yet ensuring correctness in complex, repository-level tasks remains
arXiv:2608.14558v1 Announce Type: new Abstract: Current multimodal models have demonstrated remarkable proficiency in recognizing static visual and auditory content. However, their capacity for abstra
In medium reasoning mode, it both scores higher than the 3.6 version, AND is very much more efficient (almost half requests needed, and a third less tokens generated) - at DeepSeek v4 Flash 3107 MXFP4
arXiv:2608.12779v1 Announce Type: cross Abstract: Understanding the temporal progression of symptoms in clinical narratives is critical for disease monitoring, safety surveillance, and causality asses
arXiv:2608.11994v1 Announce Type: new Abstract: We propose claim-level falsification as a principle for test-time scaling and instantiate it through Claim-Level Reliability Assessment (CLR), a trainin
arXiv:2608.11905v1 Announce Type: new Abstract: In many practical applications of generative AI systems, from tax rules to airline baggage allowance, responses to natural language queries must respect
We’re launching DeepSeek-V4-Pro today! 🚀 🔷 Major Agent upgrades with strong production gains! 🔷 Flexible reasoning effort for V4-Pro & V4-Flash: low for simple tasks, high for daily Agent workflows, m
arXiv:2608.10494v1 Announce Type: new Abstract: Earth observation (EO) agents construct scientifically valid tool workflows and ground their conclusions in current geospatial evidence. This is challen
arXiv:2608.10149v1 Announce Type: new Abstract: Due to the diversity of real-world time series, no single forecasting model consistently dominates across all samples. Ensemble learning addresses this
arXiv:2608.10004v1 Announce Type: new Abstract: Concept Bottleneck Models (CBMs) provide an interpretable framework by grounding predictions in human-understandable concepts, enabling semantic inspect
arXiv:2608.09374v1 Announce Type: new Abstract: Electrical circuit analysis requires more than recognizing components in an image. A solver must ground symbols and labels, recover latent topology, sel
arXiv:2608.07621v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have recently achieved impressive performance for end-to-end autonomous driving, yet existing approaches are primari
arXiv:2608.07512v1 Announce Type: cross Abstract: Asynchronous Video Interviews (AVIs) have become increasingly popular for personality assessment. Recent large language models (LLMs) have shown poten
arXiv:2608.07593v1 Announce Type: cross Abstract: Context-aware recommender systems have long recognized that factors such as location, time, and weather shape where and what people choose to eat. Exi
arXiv:2608.07813v1 Announce Type: new Abstract: An LLM judge deployed inside a reasoning pipeline does not merely measure quality, it decides which answer ships. We show that the cost of that decision
arXiv:2512.03057v2 Announce Type: replace-cross Abstract: We study distribution-free risk control for model routing, motivated by large language model reasoning. We formalize pointwise conditional eff
arXiv:2608.05833v1 Announce Type: new Abstract: Knowledge graph completion (KGC) aims to infer missing entities or relations from incomplete graph structures, and has evolved into multimodal knowledge
arXiv:2608.05144v1 Announce Type: new Abstract: Long-horizon reasoning requires an agentic runtime that can persist when evidence supports its current approach and pivot when measurements reveal failu
arXiv:2608.04519v1 Announce Type: new Abstract: Benchmarking machine unlearning methods is critical to understand whether sensitive knowledge is removed from large language models (LLMs) or not. Curre
arXiv:2510.21084v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown strong potential for clinical decision support through their advanced language understanding and reaso