AI News Today

arXiv:2602.10045v2 Announce Type: replace Abstract: Current instance segmentation models achieve high performance on average predictions, but lack principled uncertainty quantification: their outputs are not calibrated, and there is no guarantee that a predicted mask is close to the ground truth. To address this limitation, we introduce a conformal prediction algorithm to generate adaptive confidence sets for instance segmentation. Given an image and a pixel coordinate query, our algorithm gener

arXiv:2602.14147v2 Announce Type: replace Abstract: Diffusion language models (dLLMs) recently emerged as a promising alternative to auto-regressive LLMs. The latest works further extended it to multimodal understanding and generation tasks. In this work, we propose LaViDa-R1, a multimodal, general-purpose reasoning dLLM. Unlike existing works that build reasoning dLLMs through task-specific reinforcement learning, LaViDa-R1 incorporates diverse multimodal understanding and generation tasks in a

arXiv:2602.19710v3 Announce Type: replace Abstract: Existing Vision-Language-Action (VLA) models often suffer from feature collapse and low training efficiency because they entangle high-level perception with sparse, embodiment-specific action supervision. Since these models typically rely on VLM backbones optimized for Visual Question Answering (VQA), they excel at semantic identification but often overlook subtle 3D state variations that dictate distinct action patterns. To resolve these misal

arXiv:2603.04024v2 Announce Type: replace Abstract: Ambiguous 3D medical image segmentation often involves boundaries where different expert delineations are non-identical yet clinically plausible. Modeling such inter-observer variability requires a careful balance between diversity and anatomical fidelity: deterministic models preserve coherent volumetric structures but collapse expert disagreement into a single mask, while stochastic generative models can produce diverse samples but may introd

arXiv:2603.12144v2 Announce Type: replace Abstract: Understanding and reconstructing the 3D world through omnidirectional perception is becoming increasingly important for autonomous agents and embodied systems. However, existing 3D occupancy prediction methods are constrained by limited perspective inputs and a predefined training distribution, making them difficult to apply to embodied agents that require comprehensive and safe perception of scenes in open-world exploration. To address this, w

arXiv:2603.15932v2 Announce Type: replace Abstract: Lung cancer remains the leading cause of cancer-related mortality worldwide, with survival outcomes critically dependent on early and accurate detection. When low-dose computed tomography (LDCT) findings are indeterminate, clinicians typically defer diagnosis pending follow-up CT imaging obtained up to 12 months later, inevitably delaying treatment for patients with malignant nodules. To address this clinical gap, we propose Nodule-Aligned Mult

arXiv:2502.15631v2 Announce Type: replace Abstract: Large language models have demonstrated remarkable progress in mathematical reasoning, leveraging chain-of-thought and reinforcement learning. However, many open questions remain regarding the interplay between reasoning token usage and accuracy gains. In particular, when comparing models across generations, it is unclear whether improved performance results from longer reasoning chains or more efficient reasoning. We systematically analyze rea

arXiv:2506.09276v4 Announce Type: replace Abstract: This paper presents a state representation framework for Markov decision processes (MDPs) that can be learned solely from state trajectories, requiring neither reward signals nor the actions executed by the agent. We propose learning the minimum action distance (MAD), defined as the minimum number of actions required to transition between states, as a fundamental metric that captures the underlying structure of an environment. MAD naturally ena

arXiv:2510.06505v2 Announce Type: replace Abstract: Out-of-distribution (OOD) detection plays a crucial role in ensuring the robustness of machine learning systems deployed in real-world applications. Recent approaches have explored the use of unlabeled data, showing potential for enhancing OOD detection capabilities. However, effectively utilizing unlabeled in-the-wild data remains challenging due to the mixed nature of both in-distribution (InD) and OOD samples. The lack of a distinct set of O

arXiv:2510.22450v4 Announce Type: replace Abstract: The choice of activation function plays a critical role in neural networks, yet most architectures still rely on fixed, uniform activation functions across all neurons. We introduce SmartMixed, a novel two-phase training strategy that allows networks to learn optimal per-neuron activation functions while preserving computational efficiency at inference. In the first phase, neurons adaptively select from a pool of candidate activation functions

arXiv:2512.23236v4 Announce Type: replace Abstract: Making deep learning recommendation model (DLRM) training and inference fast and efficient is important. However, this presents three key system challenges - model architecture diversity, kernel primitive diversity, and hardware generation and architecture heterogeneity. This paper presents KernelEvolve-an agentic kernel coding framework-to tackle heterogeneity at-scale for DLRM. KernelEvolve is designed to take kernel specifications as input a

arXiv:2601.22136v2 Announce Type: replace Abstract: Agent safety benchmarks measure whether a monitor detects harm, not when. Yet timing is the difference between intervention and autopsy. We introduce StepShield, the first benchmark that treats detection timeliness as a first-class metric. On 9,429 incident-grounded code-agent trajectories, we define the Early Intervention Rate (EIR): the fraction of detected rogue trajectories where the alert fires within a k-step window after the divergence p

arXiv:2602.22600v2 Announce Type: replace Abstract: Training selects for behavior, not circuitry: many weight configurations can implement the same function. Studying any single trained neural network thus risks describing accidents of one training run rather than the computation itself. This work shifts focus from what transformers happen to do to what they must do by extracting algorithmic cores, compact subspaces that are necessary and sufficient for a task and that recur across independently

arXiv:2603.10254v2 Announce Type: replace Abstract: Synthetic tabular data generation addresses data scarcity and privacy constraints in a variety of domains. Tabular Prior-Data Fitted Network (TabPFN), a recent foundation model for tabular data, has been shown capable of generating high-quality synthetic tabular data. However, TabPFN is autoregressive: features are generated sequentially by conditioning on the previous ones, depending on the order in which they appear in the input data. We demo

arXiv:2603.11021v2 Announce Type: replace Abstract: Scalar quantization of large language models (LLMs) is fundamentally limited by information-theoretic bounds. While vector quantization (VQ) overcomes these limits by encoding blocks of parameters jointly, practical implementations must avoid the need for expensive lookup mechanisms or other explicit codebook storage. Lattice approaches address this through highly structured and dense packing. This paper explores the Leech lattice, which, with

arXiv:2604.21927v3 Announce Type: replace Abstract: Continual learning (CL) studies how models acquire tasks sequentially while retaining previously learned knowledge. Despite substantial progress in benchmarking CL methods, comparative evaluations typically keep the fine-tuning regime fixed. In this paper, we argue that the fine-tuning regime, defined by the trainable parameter subspace, is itself a key evaluation variable. We formalize adaptation regimes as projected optimization over fixed tr

arXiv:2605.02965v2 Announce Type: replace Abstract: Artificial intelligence-generated content (AIGC) has emerged as a transformative paradigm for automating the creation of diverse and customized content, giving rise to rapidly growing computational workloads in cloud data centers. It is imperative for AIGC service providers (ASPs) to strategically schedule AIGC workloads to reduce data center energy costs while guaranteeing high-quality content generation. However, the distinctive characteristi

arXiv:2605.24709v2 Announce Type: replace Abstract: Streaming reinforcement learning has emerged as an online learning paradigm that conforms to the restrictions of natural learning agents that process data incrementally, i.e. with a batch size of 1 and no replay buffer. While streaming RL has recently been shown to scale with deep function approximation with full observability, partially observable settings have remained out of reach. Truncated backpropagation through time collapses to a one-st

arXiv:2605.25451v3 Announce Type: replace Abstract: Training multimodal large language models (MLLMs) is challenged by both model and data heterogeneity. Existing systems redesign the training pipeline to address these challenges, but remain bound by a Pareto frontier between compute and memory efficiency, improving one only at the expense of the other. We present BigMac, a new training pipeline for multimodal LLMs. The core idea of BigMac is to elegantly nest the encoder and generator computati

arXiv:2606.06576v2 Announce Type: replace Abstract: In the sciences, regression tasks often require predicting high-dimensional outputs from few training examples. Multi-output Gaussian processes excel in low-data regimes but typically struggle with high-dimensional outputs. Compress-then-predict pipelines such as PCA-GP (principal component analysis plus Gaussian process regression) handle high dimensionality, but rely on bases optimized for reconstruction rather than prediction. To address thi

arXiv:2606.08343v3 Announce Type: replace Abstract: We introduce GENERIC-FNO, the first neural operator to embed the full GENERIC (metriplectic) structure of nonequilibrium thermodynamics -- reversible, energy-conserving dynamics and irreversible, entropy-producing dynamics coupled through the degeneracy conditions -- directly in function space. Existing structure-preserving neural operators enforce at most a single conservation law or reversible (Hamiltonian) structure, while thermodynamically

An AI tool to preview hairstyles and hair colors before making a real haircut decision. Comments URL: https://news.ycombinator.com/item?id=48827294 Points: 1 # Comments: 0

AI-driven platform using multi-LLM ensemble to discover and disclose critical 0-days. First case study: CVSS 9.8 unauthenticated RCE chain in Cisco CUCM 14.0 (6 stages from SQLi to root). Includes working PoC, full technical analysis, and our research on risk-driven disclosure. Happy to answer questions about the tech, AI workflow, or responsible disclosure. Comments URL: https://news.ycombinator.com/item?id=48827283 Points: 1 # Comments: 0

Article URL: https://www.moldzine.ai/ Comments URL: https://news.ycombinator.com/item?id=48827155 Points: 1 # Comments: 0

Article URL: https://aiornot.vote/ Comments URL: https://news.ycombinator.com/item?id=48827123 Points: 1 # Comments: 0

Article URL: https://www.bangordailynews.com/2026/07/02/midcoast/midcoast-culture/maine-librarians-are-helping-patrons-resist-ai-joam40zk0w/ Comments URL: https://news.ycombinator.com/item?id=48827094 Points: 10 # Comments: 0

Fascinating. ScienceAlert stories are written, fact-checked, and edited by humans, never generated by AI. Don't miss a story, subscribe here.

Article URL: https://sal4rkhn.substack.com/p/forget-the-gpu-shortage-the-real Comments URL: https://news.ycombinator.com/item?id=48827033 Points: 2 # Comments: 0

Article URL: https://time.com/article/2026/07/07/china-ai-models-alibaba-bytedance/ Comments URL: https://news.ycombinator.com/item?id=48827026 Points: 2 # Comments: 0

Ant Group's Robbyant open-sourced LingBot-Vision, a self-supervised ViT family for dense spatial perception. Masked boundary modeling makes image boundaries a native training signal. The 1B backbone matches or surpasses larger models, and initializes LingBot-Depth 2.0. The post Ant Group’s Robbyant Open-Sources LingBot-Vision: A 1B Boundary-Centric Vision Foundation Model for Dense Spatial Perception appeared first on MarkTechPost .

Article URL: https://prompt-area.com/styles Comments URL: https://news.ycombinator.com/item?id=48826962 Points: 1 # Comments: 0

Article URL: https://github.com/Medhovarsh/forkmind Comments URL: https://news.ycombinator.com/item?id=48826957 Points: 1 # Comments: 0

Article URL: https://www.economist.com/finance-and-economics/2026/07/07/ai-has-taken-over-the-stock-market-the-bond-market-is-next Comments URL: https://news.ycombinator.com/item?id=48826804 Points: 7 # Comments: 0

Article URL: https://www.reuters.com/technology/meta-expands-generative-ai-tools-with-muse-image-rollout-2026-07-07/ Comments URL: https://news.ycombinator.com/item?id=48826772 Points: 1 # Comments: 0

There is a trend that is just starting: People are cloning softwares and websites using Ai(fable 5 is doing great), what do you think what things would protect businesses from this in future? if i can clone smth easily using ai, why i would pay for it? Comments URL: https://news.ycombinator.com/item?id=48826680 Points: 2 # Comments: 2

<pre style='white-space:pre-wrap;width:81ex'>improve(diagnostics-otel): make agent-duration histograms usable beyond 10s (#96592) * improve(diagnostics-otel): tune duration/context histogram bucket boundaries The openclaw.run.duration_ms, openclaw.harness.duration_ms, and openclaw.context.tokens histograms used the SDK default bucket boundaries. The default duration buckets top out at 10s, so agent runs — which routinely take minutes — all collapse into the +Inf overflow bucket, making p95/p99 l

Article URL: https://compsec.snu.ac.kr/blog/dualview Comments URL: https://news.ycombinator.com/item?id=48826666 Points: 8 # Comments: 0

How should we ensemble time-series forecasts better? The post Information Theory and Ensemble Models appeared first on Towards Data Science .

A non-parametric variable selection for Structural VARs The post Granger Causal Networks and Indirect Feedback appeared first on Towards Data Science .