All entries

arXiv:2606.07150v1 Announce Type: cross Abstract: Agent-interoperability protocols such as A2A and MCP standardize what agents say to one another, but assume address-based transport over HTTP(S). Such

arXiv:2606.06924v1 Announce Type: new Abstract: Existing LLM routing methods typically treat a model's single response to a query as its capability label for training routers. However, because LLM gen

arXiv:2606.06966v1 Announce Type: new Abstract: Cross-domain shifts challenge Presentation Attack Detection (PAD) on ID Cards, given the restricted data available due to privacy concerns. This work pr

arXiv:2606.07047v1 Announce Type: new Abstract: Heuristics play a central role in the performance of bidirectional search algorithms, which commonly rely on two main classes. Front-to-end (F2E) heuris

FrontierCode has three task sets: Extended (150 tasks), Main (100 tasks) and Diamond (50 tasks). SOTA LLMs have significant room for improvement, with the top model earning a score of just 13.4/100 on

arXiv:2606.06856v1 Announce Type: new Abstract: Dynamic vision sensors (DVS) offer exceptional temporal resolution and dynamic range by asynchronously reporting pixel-level intensity changes. However,

further evidence that people shoveling money into AI are either bad at math or blind to risk Striking paper from Wharton. The big conclusion: AI must increase productivity 2.7x -- and quickly -- or te

This post discusses the statistical probability of a candidate receiving 30% of the general vote but zero votes in a late-night ballot count, likely raising questions about voting irregularities or da

Gary Marcus argues that large language models based on transformers quickly reach their limitations, prompting developers to add external tools as workarounds, while neurosymbolic AI—which combines ne

arXiv:2606.06576v1 Announce Type: new Abstract: In the sciences, regression tasks often require predicting high-dimensional outputs from few training examples. Multi-output Gaussian processes excel in

Google upgraded NotebookLM with Gemini 3.5 and Antigravity, a coding tool that provides more accurate information and adds code execution capabilities through a secure cloud computer with over 100 cur

Google added an empty thinking token to the Gemma 4 chat template, which stabilizes model output by suppressing 'ghost' thought channels that may appear even when thinking is deactivated. This update

arXiv:2606.06772v1 Announce Type: cross Abstract: Understanding the generalization performance of over-parameterized neural networks has become a central topic in deep learning theory. While recent ad

arXiv:2512.20963v3 Announce Type: replace-cross Abstract: Diffusion models excel at generating high-quality, diverse samples, yet they risk memorizing training data when overfit to the training object

arXiv:2606.07400v1 Announce Type: new Abstract: Many scientific problems require inferring unobserved mechanistic latent states from indirect observations. While classical approaches, including expect

arXiv:2606.06572v1 Announce Type: cross Abstract: We argue that modern generative models create structural risks for knowledge and cultural production at current, sub-AGI capability levels. We define

arXiv:2606.07239v1 Announce Type: new Abstract: The success of generative molecular design hinges on a model's steerability toward high-reward samples. Because many molecular properties are intrinsica

arXiv:2606.06967v1 Announce Type: new Abstract: Generative policies provide expressive and multimodal action distributions, making them attractive for reinforcement learning (RL) in complex continuous

arXiv:2606.07151v1 Announce Type: new Abstract: Traditional change point detection in dynamic networks assumes abrupt transitions between stationary states, overlooking scenarios of continuous evoluti

arXiv:2606.07280v1 Announce Type: new Abstract: Novel class discovery in point cloud segmentation aims to transfer knowledge from known classes to automatically identify and segment unlabeled novel cl

arXiv:2606.06550v1 Announce Type: cross Abstract: Self-supervised learning (SSL) yields powerful, context-rich representations for speech emotion recognition (SER), yet aggregating these representatio

arXiv:2606.07183v1 Announce Type: new Abstract: This work examines the semantic geometry underlying NLP models. We compare supervised vector embeddings, such as CamemBERT, with lexical co-occurrence g

Clem Delangue discusses using local AI models and LlamaCPP to prepare for a flight to NYC without internet access, highlighting the utility of offline AI tools for travel preparation. The post demonst

arXiv:2606.06881v1 Announce Type: new Abstract: Blood glucose forecasting models are foundational for modern diabetes management systems, as reliable short-term predictions can enable proactive interv

Good take My guess is - demand for intelligence is near infinite - but 80% of workloads will be running on 99% cheaper models within 12-18 months - 20% of workloads will still run on latest gen models

Kif Leswing / CNBC: Google and Nvidia are helping Apple with Apple Foundation Model Cloud Pro, which Apple says is comparable to Gemini frontier models and runs on Nvidia GPUs — - Apple showed off Sir

Abner Li / 9to5Google: Google lowers the price of its Google AI Plus plan to 4.99 per month, down from 7.99, and doubles the included storage to 400GB — Google announced today that its AI Plus subscri

Ivan Mehta / TechCrunch: Google upgrades NotebookLM, which now runs on Gemini 3.5 and Antigravity, to deliver new agentic capabilities and more advanced reasoning for AI Ultra users — Google on Monday

arXiv:2606.06532v1 Announce Type: new Abstract: Despite significant progress in agentic long video understanding, existing methods still lack detailed motion comprehension coupled with an efficient me

arXiv:2606.07102v1 Announce Type: cross Abstract: We propose GP-Adapter, a training-free framework that augments CLIP (Contrastive Language-Image Pre-training) with Gaussian Process (GP) uncertainty m

arXiv:2606.07475v1 Announce Type: cross Abstract: Node classification in graph neural networks (GNNs) has been widely applied in various fields of graph analysis. GNNs achieve high-accuracy node class

arXiv:2606.06892v1 Announce Type: new Abstract: Scalable data attribution methods typically assign isolated utility scores to individual training examples. This prevalent additive assumption fundament

This paper from researchers at Hazy Research (Jon Saad-Falcon and Avanika Narayan) appears to present novel research findings, likely related to machine learning, language models, or AI systems given

Great tips. In practice, this is how it roughly looks to run agents autonomously for hours or days. /goal or /loop to keep it going. Verification is crucial here. Seeing a number of benchmarks showing

Great to see AI maturing and finally adopting what we've been preaching for a while now: multi-model workloads! It will go even further progressively though with most companies not only using dozens o

Grok Imagine Video 1.5 Preview has officially taken the #1 spot in Image-to-Video generation on Design Arena • #1 overall with a 1357 Elo rating • Massive 49-point lead over the next-best model • Ahea

arXiv:2512.09084v3 Announce Type: replace Abstract: The Kolmogorov-Arnold representation theorem offers a theoretical alternative to Multi-Layer Perceptrons (MLPs) by placing learnable univariate func

arXiv:2606.07024v1 Announce Type: new Abstract: Multi-modal approaches used for 3D CAD generation require substantial computational resources, necessitating efficient training. To address this, we pro

arXiv:2603.20967v2 Announce Type: replace-cross Abstract: One of the most common machine learning setups is logistic regression. In many classification models, including neural networks, the final pre

arXiv:2606.06833v1 Announce Type: cross Abstract: Automatic Speech Recognition (ASR) systems operating in real-time settings must process acoustic input under strict temporal constraints, where transc

This post likely explains the concept of loops in programming or automation workflows, covering how they function and their practical applications for automating repetitive tasks. It probably includes

arXiv:2209.00188v4 Announce Type: replace-cross Abstract: Long-latency load requests continue to limit the performance of high-performance processors. To increase the latency tolerance of a processor,

arXiv:2606.06986v1 Announce Type: new Abstract: While green finance has become a key instrument for low-carbon city transitions, its actual decarbonization effects and transmission mechanisms remain u

User seeks guidance on PDF processing methods for local AI agents built with Ollama, comparing approaches like PDFPlumber extraction, vector database RAG systems, and alternative techniques for accura

arXiv:2606.07316v1 Announce Type: cross Abstract: Byzantine collaboration among large-language-model agents requires a finality-control primitive: given delivered stochastic, structured natural-langua

arXiv:2606.07044v1 Announce Type: new Abstract: Accurate and coherent passenger demand forecasting is essential for Urban Rail Transit (URT) operations. Passenger demand has a hierarchical structure i