AIPULSE
Live

Discover

Latest research papers and top Hacker News stories

Latest Papers24
1
AINLPAI

OmniScientist: An Omni-Modal Omni-Discipline AI Scientist

Recent advances in foundation models have enabled AI scientists to automate increasingly complete research workflows, from hypothesis generation and code execution to manuscript preparation. Yet workflow coverage alone does not provide access to the full evidence on which scientific discovery depends. Existing systems typically reason over text, code, labels, or precomputed summaries, leaving scientifically decisive spatial, temporal, cross-channel, and procedural relations unavailable to the agent. We introduce OmniScientist, an end-to-end, omni-modal AI scientist that conducts multidisciplin

Bobo Li, Hao Fei, Tianjie Ju·3 days ago
2
RoboticsAIVision

HumanTracker: Towards Comprehensive and Human-Aligned Motion Tracking Benchmark

Humanoid motion tracking is central to teleoperation and whole-body imitation, yet evaluation often disagrees with what people perceive in videos. Kinematic errors average per-frame pose differences but miss the physical artifacts that matter most, particularly unstable support and incorrect contacts such as foot skating and mistimed touch-downs. Meanwhile, widely used test suites are small and lack the diversity needed to stress contact-rich, long-horizon behaviors. We introduce HumanTracker to make humanoid tracking evaluation both perceptually aligned and scalable. The HumanTracker benchmar

Dairu Liu, Zekun Qi, Jiayu Zeng·3 days ago
3
MLMLcs.CC

Defensive Boosting for Online Probabilistic Forecasting

We study online probabilistic forecasting of binary outcomes chosen by an adaptive adversary. Given an online learning algorithm for a weak hypothesis class $H$, we would like to efficiently obtain two incomparable guarantees that existing online boosting techniques provide separately. Online gradient boosting competes in Brier score with the best predictor induced by the span of $H$ on every sequence, but promises nothing when the span does not contain an accurate predictor. Online weak-to-strong boosting drives classification error to zero under a weak-learning condition, but promises little

Georgy Noarov, Aaron Roth·3 days ago
4
MLML

Exponential Convex Calibration Dimension for the Multi-Label Jaccard Measure

The per-instance Jaccard score, or intersection over union (IoU), is standard in multi-label classification and binary segmentation. With $s$ labels, its loss matrix has $2^s$ outcomes and reports. Under the convention $\mathrm{Jac}(\varnothing,\varnothing)=1$, we prove that the Jaccard score, shifted-loss, and ordinary loss matrices are nonsingular and that the loss columns have affine dimension $2^s-1$. The proof combines a finite MinHash Gram representation with Boolean Möbius inversion. For exact calibration, we prove $2^{s-1} \leq \mathrm{CCdim}(L^{\mathrm{Jac}}) \leq 2^s-1$. The lower bo

Mingyuan Zhang·3 days ago
5
AIAIcs.SE

QuoteBench: How Matched Scores Can Hide Command-Path Failures

LLM coding agents issue Bash commands through interfaces that may serialize, wrap, and reparse model output. Matched execution scores alone cannot distinguish command-generation errors from failures introduced after generation. QuoteBench measures this boundary with exact final-state validation on 56 one-shot tasks from 14 incident-derived families, crossing the generation contract with the execution transport around one deliberately unescaped added parser. Escaping at the interpolation point reproduces each replayed reply's raw-path outcome, so any recovery under a disclosed boundary must com

Shangao Li, Yao Zhang, Volker Tresp·3 days ago
6
NLPAIML

LittleLearner: Language Models Under Pedagogically Controlled Knowledge Exposure

Modern language models are trained on heterogeneous web-scale text corpora. Consequently, studying knowledge and skill acquisition is difficult, as prior exposure to related content is hard to characterize. To address this challenge, we introduce LITTLECURRICULUM, a curated 88B-token pretraining corpus tailored to U.S. elementary school material, explicitly excluding concepts, facts, and vocabulary taught above Grade 5. Training a 5B-parameter LLM from scratch on LITTLECURRICULUM yields LITTLELEARNER, a model with sufficient language competence for open-ended evaluation, yet with clear knowled

Fanfei Li, Jana Zeller, Manuel Prada-Corral·3 days ago
7
MLML

DARTree: Speculative Diffusion Decoding with Autoregressive Draft Trees

Speculative decoding losslessly accelerates autoregressive language models by verifying multiple draft tokens in parallel. Diffusion-based drafters further reduce proposal latency by predicting an entire token block in parallel, but their position-wise distributions are marginal rather than conditioned on tokens selected along each draft path. Existing recurrent correction incorporates causal information along a single draft chain, whereas diffusion-based tree construction broadens candidate coverage without carrying this correction along individual branches. We introduce DARTree, a training-f

Tianyi Li, Yaxin Luo, Xinyi Shang·3 days ago
8
MLAIcs.LO

Vero: Can AI Agents Build Formally Verified Software Repositories?

AI agents are increasingly used for programming, but do not provide any guarantee on the correctness of generated code. Verified code generation, in which an agent produces both an implementation and a machine-checked proof of its specification, offers a stronger path toward trustworthy AI-generated software. Existing benchmarks in this direction either focus on individual functions or only evaluate proof generation with provided implementations. It is still an open question whether agents can make coherent implementation and proof choices across real multi-module codebases. To bridge this gap

Zhe Ye, Hantao Lou, Yuechun Sun·3 days ago
9
MLcs.IT

Exponential quantum advantage for learning signals with a single qubit

Quantum technology has the potential to transform scientific discovery, but quantum advantages often require processing capabilities well beyond the reach of experimental platforms. We show that coupling a single controllable qubit to an otherwise conventional sensor can exponentially reduce the number of measurements required to learn classical signals. These rigorous quantum advantages apply to fundamental sensing tasks, including learning Fourier coefficients, extracting temporal correlations from time-varying signals, and estimating transformations of physical observables. Using a supercon

Ishaan Kannan, Sridhar Prabhu, Saeed A. Khan·3 days ago
10
MLAIMLcs.IT

The data geometry of masking diffusion: Certified-optimal schedules via unmasking growth complexity

We study masking diffusion for discrete sampling and introduce a path-resolved measure of data geometry called the \emph{unmasking growth complexity} ({\textsf{UGC}\xspace}). Its local increments directly control Kullback--Leibler (KL) discretization error, yielding a unified analysis of Bernoulli-subset and fixed-cardinality unmasking schemes. In log-reveal-odds coordinates, this structure yields optimized single-block and multi-block schedules, and quantifies the gains from adapting computational effort to data geometry. Crucially, we show how {\textsf{UGC}\xspace} increments can be estimate

Martin J. Wainwright·3 days ago
11
MLVisionML

Intervention-Aware Clinical World Model for Post-Op Outcome Forecasting in Cardiology

Many clinical prediction models treat post-intervention outcomes as a one-step mapping from baseline measurements to a future endpoint. However, recovery after a procedure often unfolds as an irregular trajectory: clinical observations, medication changes, repeat interventions, and physiological measurements are recorded asynchronously and can change risk assessment over time. We propose an intervention-aware clinical world model that represents each patient with a structured latent state and evolves it through time-ordered post-intervention events. The model first encodes baseline imaging int

Yunsung Chung, Yingshuo Liu, Abboud F. Hassan·3 days ago
12
NLPAINLP

DFM Mimir v1: An Open HRM Delivering Frontier Performance at 1B Parameters Using Only Permissible Post-Training Data

Current large language model development relies on massive, often non-permissible datasets, creating a high barrier for researchers committed to open-source and ethically sourced data. We introduce Mimir v1, a 1-billion-parameter language model based on the Hierarchical Reasoning Model (HRM) architecture, that is trained from scratch and delivers highly competitive performance for English and sets a new state of the art for Danish using only permissible post-training data. Trained on a mixture of 161 datasets, Mimir v1 outperforms the original HRM-Text 1B and competes with larger frontier mode

Peter Schneider-Kamp, Jacob Nielsen, Gianluca Barmina·3 days ago
13
MLcs.DS

Bagging Robustly Learns VC Classes with Linear Sample Complexity

We revisit the problem of learning predictors robust to adversarial examples at test-time. We prove that VC classes are adversarially robustly learnable with sample complexity linear in the VC dimension $d$, providing an exponential improvement over the previous upper bound of Montasser, Hanneke, and Srebro (2019). Remarkably, this result is achieved with a simple improper algorithm that combines the classic heuristic bagging (bootstrap aggregation) of Breiman (1996) with robust empirical risk minimization (RERM). Our algorithm computes RERMs on $O(d^\star)$ independent bootstrap samples and o

Omar Montasser·3 days ago
14
VisionMLVision

TabSOM: A tabular-to-image encoding method based on self-organizing maps

Tabular-to-image methods have emerged as novel approaches to leverage the high predictive performance of convolutional neural networks and vision transformers. They convert tabular data into image representations, mapping each feature at a fixed pixel location derived from a dimensionality-reduction method (e.g., t-SNE, UMAP, PCA). However, they encode only the marginal value of each feature and discard information about feature relationships. We propose TabSOM, a tabular-to-image encoding built on the Self-Organizing Map (SOM), which provides: (i) a spatial layout in which every input feature

David Chushig-Muzo, María Ángeles Rodríguez de Cara, Eva Milara·3 days ago
15
ML

On the Structural Limits of Machine Learning Decision Systems: An Information-Theoretic, Interaction-Based, and Stochastic-Dynamical Perspective

Machine learning procedures are commonly evaluated in terms of predictive accuracy and computational efficiency. However, their achievable performance is fundamentally constrained by structural properties of the underlying data-generating process, which are formalized in terms of informational bounds. In this work we examine intrinsic limits of data-driven decision systems from an information-theoretic and interaction-based perspective. We analyze minimal achievable error in classification through Fano-type bounds and precision limits in parametric estimation via the Cramér-Rao inequality, emp

Nestor R. Barraza, Gabriel Pena·3 days ago
16
ML

Equivariant learning of a transferable three-dimensional classical density functional

Liquids exhibit collective behavior that depends sensitively on thermodynamic conditions, interfaces and confinement, yet predicting each new state commonly requires a separate atomistic simulation. Classical density functional theory offers a reusable variational description, but its central excess free-energy functional is generally unknown, and learned approximations have largely remained restricted to planar or lower-dimensional settings. Here we show that this functional can be learned directly from fully three-dimensional equilibrium density fields while preserving spatial symmetry and v

Bingqing Cheng·3 days ago
17
MLNLPVision

Intern-S2-Preview: Scientific Agentic Foundation Model

Scientific discovery increasingly requires AI systems that can reason over scientific evidence of heterogeneous modalities, interact with scientific tools and environments, and sustain progress across long task horizons. We present Intern-S2-Preview, a series of scientific agentic foundation models designed to support multimodal scientific understanding, reasoning, generation, and long-horizon tasks. The training pipeline begins with scientific multimodal pre-training over rendered scientific documents, interleaved image-text data, and diverse scientific corpora. Starting from the pretrained c

Lei Bai, Jiaqi Cao, Chiyu Chen·3 days ago
18
MLML

Sparse Orthogonal Regression Technique: A Spectral Framework for Equation Discovery, Approximation, and Integration

We develop the Sparse Orthogonal Regression Technique (SORT), a sparse spectral framework for learning orthonormal-basis expansions from noisy and irregularly sampled data. SORT estimates expansion coefficients directly from observations using L1-regularized regression, avoiding explicit quadrature or analytic inner-product evaluation. The central application is data-driven discovery of ordinary differential equations: vector fields are represented in chosen orthogonal bases and learned as sparse coefficient expansions. This provides a complementary route to symbolic regression, grammar-based

Sabin Roman, Ljupco Todorovski, Saso Dzeroski·3 days ago
19
VisionMLVision

TraVEL: Trajectory-Guided Video Embedding Learning for Driving-Video Retrieval

Efficiently retrieving relevant clips from large-scale driving logs is essential for data curation, model development, and safety analysis. Structured and rule-based retrieval systems can explicitly target driving events, but typically require expert-defined rules, auxiliary data, and multi-stage perception pipelines. Multimodal embedding models offer a simpler and more efficient alternative by representing each video with a single searchable vector. However, general-purpose models often rely on shortcuts from static scene context and struggle to distinguish motion-centric events, such as turn

Yi-Chung Chen, Philip Jacobson, Tom Lampo·3 days ago
20
AIAI

AlayaWorld: Interactive Long-Horizon World Modeling - Full Technical Report (v1.1)

This report presents an improved version of AlayaWorld. While the backbone architecture, chunk-wise autoregressive generation scheme, and training data remain unchanged from the previous release, we substantially revise how conditioning signals are represented and integrated into the model. The new design is guided by a simple principle: conditioning signals should match the generated content as closely as possible in both latent representation and temporal structure. To this end, we make two major changes. First, we replace the previous depth-warping-based spatial memory with a streaming 3D p

AlayaWorld Team, Kaipeng Zhang, Chuanhao Li·3 days ago
21
NLPAINLP

Toward a Gricean Retreat: Probing LLMs for Knowledge Boundaries and Referent Specificity

When asked about entities outside their knowledge boundary, LLMs routinely fabricate plausible-sounding details rather than backing off to safer, more general claims. We frame this failure through a Gricean lens: a cooperative speaker who is uncertain about a referent retreats up the specificity hierarchy, trading informativeness for truthfulness. We ask whether LLMs have the ingredients to perform this retreat. Using a T-REx-based benchmark that varies entity familiarity and referent specificity, we probe models to answer two questions: (i) do their activations encode whether a referent falls

Dananjay Srinivas, Saksham Khatwani, Maria Pacheco·4 days ago
22
MLAINLP

Synthetic Persona Pretraining: Alignment from Token Zero

As language-model-based AI is increasingly deployed in autonomous settings, aligning its goals and values with those of humans becomes critical. Today, alignment, and the assistant identity itself, are typically introduced only after pretraining, once behavioral priors are already established. This can make values a thin overlay, rather than deeply rooted, and facilitate subsequent misalignment. Pursuing a different paradigm, we introduce Synthetic Persona Pretraining (SPP), which installs the desired assistant persona from token zero in pretraining. First, we annotate pretraining documents wi

Julian Minder, Viktor Moskvoretskii, Raghav Singhal·4 days ago
23
AINLPAI

MARC v1: An Open-Source Multi-Agent Framework for Clinical AI Reasoning and Coordination

We present Multi-Agent Reasoning and Coordination (MARC), an open-source framework that replaces monolithic LLM prompting with deterministic multi-agent orchestration for clinical reasoning. MARC coordinates role-specialized agents for extraction, reasoning, answer generation, and evaluation, with explicit context passing and traceable intermediate outputs, enabling stage-wise failure attribution. We additionally introduce a Decomposer module that generates task-specific agent prompts from a plain-language description, eliminating manual prompt engineering. The framework supports both API-base

Saisha Shetty, Satvik Tripathi, Austin Lin·4 days ago
24
AI

AaLLM: An End-to-End Analog Circuit Design Framework from Topology Generation to Sizing Using Large Language Models

Analog circuit design is a time-consuming, iterative process in a nonlinear and high-dimensional design space that relies heavily on expert intuition. Among recent developments, LLMs have introduced a promising approach by bringing natural language reasoning to circuit design tasks. The majority of conventional LLM-based approaches provide fragmented solutions that focus either only on sizing or topology generation. These methods require adding specific technical knowledge manually, which is inefficient and prone to hallucinations during circuit sizing. Moreover, the inherent trade-off in meet

Mohammed Ayman Habib, Rylan Hart, Morteza Fayazi·4 days ago
Hacker News AI24
1
2.0k

Claude Code's source code has been leaked via a map file in their NPM registry

HN·5 months ago
2
1.9k

I'm Tired of Talking to AI

HN·3 months ago
3
1.9k

Claude Code is steganographically marking requests

HN·about 2 months ago
4
1.7k

Claude Opus 4.7

HN·4 months ago
5
1.6k

Apple sues OpenAI, accuses ex-employees of stealing trade secrets

HN·about 1 month ago
6
1.5k

Claude Opus 5

HN·24 days ago
7
1.5k

Zig Creator Calls Spade a Spade, Anthropic Blows Smoke

HN·about 1 month ago
8
1.5k

Claude Opus 4.8

HN·3 months ago
9
1.4k

Google Chrome silently installs a 4 GB AI model on your device without consent

HN·3 months ago
10
1.3k

GPT-5.5

HN·4 months ago
11
1.3k

I’ve joined Anthropic

HN·3 months ago
12
1.3k

Project Glasswing: Securing critical software for the AI era

HN·4 months ago
13
1.3k

Writing by hand is good for your brain

HN·25 days ago
14
1.2k

GPT-5.6

HN·about 1 month ago
15
1.2k

The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

HN·5 months ago
16
1.1k

Claude Code refuses requests or charges extra if your commits mention "OpenClaw"

HN·4 months ago
17
1.1k

Tell HN: Docker pull fails in Spain due to football Cloudflare block

HN·4 months ago
18
1.1k

Claude Sonnet 5

HN·about 2 months ago
19
1.1k

China’s open-weights AI strategy is winning

HN·28 days ago
20
1.1k

An OpenAI model has disproved a central conjecture in discrete geometry

HN·3 months ago
21
1.1k

Issue: Claude Code is unusable for complex engineering tasks with Feb updates

HN·4 months ago
22
1.1k

OpenAI and Hugging Face address security incident during model evaluation

HN·26 days ago
23
1.0k

Sixty percent of US consumers say 'AI' in brand messaging is a turnoff

HN·2 months ago
24
1.0k

Local AI needs to be the norm

HN·3 months ago