AI News Today

arXiv:2607.07978v1 Announce Type: cross Abstract: Quantum reservoir computing uses a fixed quantum circuit as a feature generator and trains only a simple linear readout on top of it. This makes it cheap to train and free of the optimisation problems that affect many quantum machine-learning models. A natural worry is that the very large feature space the circuit produces might inflate apparent performance without adding anything real. This paper provides two things. First, it gives a complete,

arXiv:2607.07989v1 Announce Type: cross Abstract: Large language model (LLM) based multi-agent systems enable complex problem solving through coordinated reasoning and action, but their distributed structure also introduces new challenges in diagnosing system-level failures. When an execution fails, identifying which agent is responsible and at what point the trajectory first becomes irreversibly misdirected is difficult due to long-horizon interactions and tightly coupled agent behaviors. In th

arXiv:2607.08011v1 Announce Type: cross Abstract: Large language models have enabled powerful code completion systems that assist developers by predicting subsequent lines of code. However, these models remain vulnerable to backdoor attacks, where malicious fine-tuning data covertly implants unsafe behaviors. Despite advances in defensive techniques, adaptive and sophisticated backdoor attacks still evade detection and mitigation. We present CodeTracer, a forensic framework that traces malicious

arXiv:2606.30308v2 Announce Type: replace Abstract: 4D hand motion reconstruction from egocentric video is bottlenecked by clear limitations of existing methods: image-based pipelines depend on a detector that fails under heavy occlusion, while video-based methods rely on temporal modules learned only from scarce hand-pose annotations, a narrow signal insufficient to model motion dynamics, occlusion reasoning, and hand-object interaction. These capabilities, however, are exactly what video gener

arXiv:2303.04203v4 Announce Type: replace-cross Abstract: The theory of computation was built to answer Turing's question: what is effectively calculable by an unbounded, immortal, disembodied agent following rules? Intelligence answers a different question (nature's): what can a \emph{finite}, mortal, energy-limited agent do quickly enough to survive in a non-stationary world? We argue that a complete answer requires two operators: \emph{computation} and \emph{memorizaion}. Computation, $\dpar$

arXiv:2502.20805v3 Announce Type: replace-cross Abstract: Hand-object interaction(HOI) is the fundamental link between human and environment, yet its dexterous and complex pose significantly challenges for gesture control. Despite significant advances in AI and robotics, enabling machines to understand and simulate hand-object interactions, capturing the semantics of functional grasping tasks remains a considerable challenge. While previous work can generate stable and correct 3D grasps, they ar

arXiv:2507.05240v2 Announce Type: replace-cross Abstract: Vision-and-Language Navigation (VLN) in real-world settings requires agents to process continuous visual streams and generate actions with low latency grounded in language instructions. While Video-based Large Language Models (Video-LLMs) have driven recent progress, current VLN methods based on Video-LLM often face trade-offs among fine-grained visual understanding, long-term context modeling and computational efficiency. We introduce St

arXiv:2510.18999v3 Announce Type: replace-cross Abstract: Reconstructing signed distance functions (SDFs) from point cloud data benefits many robot autonomy capabilities, including localization, mapping, motion planning, and control. Methods that support online and large-scale SDF reconstruction often rely on discrete volumetric data structures, which affects the continuity and differentiability of the SDF estimates. Neural network methods have demonstrated high-fidelity differentiable SDF recon

arXiv:2607.08045v1 Announce Type: cross Abstract: Angular radio maps describe the received-power distribution over the angle of arrival and underpin beam selection and receiver localization in sixth-generation (6G) networks. Predicting the angular power spectrum (APS) from geometry is difficult, because the mapping is ill-posed in non-line-of-sight (NLOS) conditions and must generalize to unseen environments. Distortion-minimizing regressors return the conditional mean, which over-smooths the sp

arXiv:2607.08066v1 Announce Type: cross Abstract: Chain-of-thought (CoT) monitoring is a promising safety mechanism for AI agents, based on the premise that visible reasoning traces can surface misaligned or deceptive behavior. While effective in standard scenarios, recent work highlights that LLMs remain vulnerable to persuasion-based jailbreaks, where natural-language arguments override model constraints. We stress-test whether this vulnerability extends to monitoring LLMs: can an adversarial

arXiv:2607.08107v1 Announce Type: cross Abstract: Two-tower retrievers compress each user into a single embedding, limiting their ability to serve diverse interests. Multi-interest models give each user several heads scored by a maximum inner product, but their hard-routing training under-utilizes heads (routing collapse) and gives no per-user estimate of how much each interest matters for serving. We present \textbf{BACH} (\emph{Bayesian Admixture of Contrastive Heads}), which casts multi-inter

arXiv:2607.08124v1 Announce Type: cross Abstract: The behavior of an LLM agent is determined not only by the underlying model, but also by its harness: the executable program that constructs context, invokes tools, verifies intermediate results, and recovers from failures. Existing approaches optimize such harnesses before deployment, searching training or development data for a fixed agent workflow that is then frozen at test time. This limits adaptation when the test distribution, failure mode

arXiv:2607.08137v1 Announce Type: cross Abstract: Federated reinforcement learning (FRL) is crucial for enabling collaborative learning across multiple agents without sharing raw data, thereby enhancing privacy and scalability in the decision-making process within dynamic vehicular environments. However, poisoning attacks pose a significant threat to the security and reliability of FRL-based systems, particularly in safety-critical autonomous driving, where this vulnerability remains largely une

arXiv:2607.08168v1 Announce Type: cross Abstract: Existing methods for automatic music transcription are often limited to single-instrument recordings or fail on complex, real music mixes. Although previous work utilizes synthetic training data, the resulting models generalize poorly, leading to largely unusable transcription output in realistic, multi-instrument settings. In this work, we analyze the effectiveness of synthetic data for pre-training while combining it with fine-tuning on real mu

arXiv:2607.08197v1 Announce Type: cross Abstract: In cloud computing, the public cloud service providers (CSPs) can provide cloud storage as the primary service while providing additional machine learning (ML)-based services by using the clients' data in storage. This business model extends the border of cloud computing services and brings in new business growth possibilities. Although it is promising, the model also brings in security concerns since the public commercial cloud cannot be fully t

arXiv:2607.08316v1 Announce Type: cross Abstract: Vehicle intention prediction is a pivotal aspect in the agility and safety of autonomous vehicles in all driving scenarios; if genuine enhancement of autonomous vehicles are required, we need to make them adopt human interpretation of driver's intention especially in cases that require a lot of human interaction as well as complex driving behaviors like the ones at intersections, roundabouts and emergency cases such as sudden stops where vehicle

arXiv:2607.08335v1 Announce Type: cross Abstract: Policy-based approaches to Bayesian experimental design (BED) allow the learning of deep policy networks that adaptively make intelligent design decisions based on previously collected data. However, the training of such policies is often held back by a fundamental challenge: the double intractability of the expected information gain (EIG). This necessitates expensive or complex approximations that restrict the effort one can invest in optimising

arXiv:2607.08370v1 Announce Type: cross Abstract: We derive bounds for the volume of tubular neighbourhoods of smooth Pfaffian hypersurfaces, generalising known results for algebraic varieties. The bounds are given in terms of the Pfaffian format of the defining functions. As an application, we obtain tail bounds on the probability distribution of a condition number measuring the robustness of neural network classifiers with Pfaffian activation functions, in both the uniform and Gaussian setting

arXiv:2607.08391v1 Announce Type: cross Abstract: Making tradeoffs between execution latency and result utility (i.e., anytime computing) for adapting to dynamic operational requirements has been shown to enhance the performance of cyber-physical systems. In this work, we focus on enabling anytime computing for deep neural networks (DNNs) that process LiDAR point clouds for 3D object detection. We propose a novel method that enables multi-resolution inference for models that process point clouds

arXiv:2607.08392v1 Announce Type: cross Abstract: Amortized neural inverse design typically remains closed-world: component choices are fixed vocabulary tokens, coordinate grids are frozen at training time, and continuous variables are discretized into sequence tokens. Multilayer optical coatings are an industrially important instance, coupling material sequence, layer thickness and wavelength-dependent response. We present IrisFlow, a query-based, open-vocabulary flow-matching framework instant

arXiv:2607.08400v1 Announce Type: cross Abstract: LLM agents reach users through resellers, who may rebrand a developer's agent or substitute a cheaper model. When provenance is disputed, attribution rests on the trajectory log (the record of tool calls, observations, and executed actions, not the model's reasoning), which the reseller stores and processes to meter usage. A watermark must therefore survive an adversary with full read/write access to the very evidence it is detected from; existin

arXiv:2607.08404v1 Announce Type: cross Abstract: Current computational approaches for drug design typically focus on generating molecules conditioned on specific targets or general molecular properties, often neglecting the influence of disease context on target behavior and therapeutic outcomes. To address this gap, we introduce DrugGen-2, a novel generative model that designs small molecules conditioned on both disease ontology and target protein sequences. DrugGen-2 was developed by fine-tun

arXiv:2607.08427v1 Announce Type: cross Abstract: Achieving nanosecond-scale inference latency for deep neural networks (DNNs) has become a primary architectural concern for latency-critical applications. While Field-Programmable Gate Arrays (FPGAs) offer a promising substrate for low-latency inference, conventional FPGA accelerators remain arithmetic-centric, using LUTs primarily as building blocks for numerical operators and peripheral logic. In contrast, recent LUT-native neural networks trea

arXiv:2607.08444v1 Announce Type: cross Abstract: In this paper, we study quantile-based distributional reinforcement learning from the perspective of statistical efficiency. We focus on distributional policy evaluation, whose goal is to characterize the return distribution, namely the distribution of discounted cumulative rewards under a given policy. To obtain a finite-dimensional representation of the return distribution, we consider the quantile fixed point $\eta_m$ induced by the quantile-p

arXiv:2607.08533v1 Announce Type: cross Abstract: Understanding perceptual differences between autistic and neurotypical adults requires behavioral assays that are sensitive, reliable, and mechanistically informative. Facial emotion perception is a useful test case because group differences have been reported, but findings vary across studies. Here we show that this variability may reflect image-level sparsity: autistic-neurotypical differences in emotion judgments were concentrated in a small s

arXiv:2607.08545v1 Announce Type: cross Abstract: End-to-end neural audio models achieve high-fidelity compression and generation. We might read that performance as evidence they directly represent interpretable features such as pitch and timbre, but a model can produce plausible outputs without doing so. A model may encode these features in any reachable basis, but regardless of which, the features are well described as compositions of time-frequency-localized primitives. Whether state-of-the-a

arXiv:2607.08757v1 Announce Type: cross Abstract: Score matching controls average error under the forward marginals, but a discretized reverse-time sampler evaluates the learned score along its own trajectory. We show that small forward-marginal error does not guarantee numerical stability. We construct a single smooth score field with arbitrarily small forward-marginal $L^2$ error. The learned reverse-time process is nonexplosive, has moments of every order, and can be arbitrarily close to the

arXiv:2310.07895v2 Announce Type: replace Abstract: This paper presents a method to efficiently classify the gastroenterologic section of images derived from Video Capsule Endoscopy (VCE) studies by exploring the combination of a Convolutional Neural Network (CNN) for classification with the time-series analysis properties of a Hidden Markov Model (HMM). It is demonstrated that successive time-series analysis identifies and corrects errors in the CNN output. Our approach achieves an accuracy of

Hi everyone, We're releasing Audar-ASR-V1, the first public release from AudarAI. AudarAI is building multilingual audio intelligence, beginning with speech recognition for Arabic and its many dialects. We start with Arabic—not because it is our destination, but because it is where we believe we can make the greatest impact. From there, we continue expanding toward multilingual audio intelligence for the world. This release includes: • Flash & Turbo open-weight models • Technical report • Evalua

The move comes as Manus' investors seek alternatives after Beijing ordered Meta to unwind its acquisition of the AI startup.

<p> Proactive agent teams you manage like humans </p> <p> <a href="https://www.producthunt.com/products/yagni?utm_campaign=producthunt-atom-posts-feed&utm_medium=rss-feed&utm_source=producthunt-atom-posts-feed">Discussion</a> | <a href="https://www.producthunt.com/r/p/1192566?app_id=339">Link</a> </p>

Article URL: https://blogs.microsoft.com/on-the-issues/2026/07/09/responsibly-building-the-ai-future/ Comments URL: https://news.ycombinator.com/item?id=48855168 Points: 2 # Comments: 0

Article URL: https://twitter.com/MKBHD/status/2075375524684218655 Comments URL: https://news.ycombinator.com/item?id=48855151 Points: 2 # Comments: 1

A native .NET LLM inference engine for GGUF models — with a command-line tool, a browser chat server, and Ollama- & OpenAI-compatible APIs for programmatic access. Comments URL: https://news.ycombinator.com/item?id=48855138 Points: 2 # Comments: 0

Comments

<pre style='white-space:pre-wrap;width:81ex'>fix(cron): channel failure alerts drop when global webhook failure destination is set (#102445) * fix(cron): keep channel-shaped failure destinations from inheriting webhook mode * test(cron): prove channel failure destination announces under global webhook * test(gateway): prove cron channel failure destination under global webhook * fix(cron): harden failure destination mode inference Tighten the resolver invariant, reuse focused test fixtures, and

Article URL: https://github.com/arthiccc/gcolab-whisper Comments URL: https://news.ycombinator.com/item?id=48854950 Points: 1 # Comments: 1

Article URL: https://github.com/benri-ai/slack-debloat Comments URL: https://news.ycombinator.com/item?id=48854923 Points: 2 # Comments: 0

<pre style='white-space:pre-wrap;width:81ex'>fix(cron): preserve cron context in session entry for async completion wakes (#101078) * fix(cron): preserve cron context in session entry for async completion wakes (#99919) Persist bootstrapContextRunKind on the session entry after cron agent runs, and restore provider/model/thinking/runKind from the session entry into directAgentParams when an async completion wake (e.g. media generation) resumes a cron session. Before this fix, async completion wa

Article URL: https://huggingface.co/EximiusLabs/fusion-embedding-1-2b-preview Comments URL: https://news.ycombinator.com/item?id=48854893 Points: 7 # Comments: 0