arXiv AI
5d ago
PPAPlace: Differentiable Cross-Stage Objectives for Chip Placement Optimization
arXiv:2608. 13790v1 Announce Type: cross Abstract: Macro placement significantly affects a chip's post-route performance, power, and area (PPA).
Benchmarks and evaluation
Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv AI
5d ago
Voxel-based 3D Facies Segmentation from Seismic Data: A Comparative Study
arXiv:2608. 14058v1 Announce Type: cross Abstract: Seismic facies segmentation has emerged as a significant challenge in geophysics, requiring robust methods and systems to effectively identify geologically analogous facies with limited labeled data.
arXiv AI
5d ago
Reaction-Transformation-Aware Flow Matching for Generalizable Transition State Generation
arXiv:2608. 14076v1 Announce Type: cross Abstract: Transition-state (TS) structures define the energetic barriers and mechanistic pathways of elementary chemical reactions, yet their identification remains computationally demanding because conventional saddle-point searches require expensive quantum-mechanical calculations.
arXiv AI
5d ago
Rewrite Once, Validate Anywhere: Producing OWL-Aware SHACL Constraints (Extended Version)
arXiv:2608. 14104v1 Announce Type: cross Abstract: The Shapes Constraint Language (SHACL) is a W3C recommendation to express syntactic constraints, called shapes, on RDF graphs.
arXiv AI
5d ago
Forecast Collapse in Time-Series Foundation Models
arXiv:2608. 14106v1 Announce Type: cross Abstract: When forecasting hourly returns for 1,000 US equities, we observe an unexpected phenomenon: predictions become nearly flat and show poor stock ranking, as measured by cross-sectional correlation.
arXiv AI
5d ago
From Fixed Grids to Moving Particles:A Transferable Latent Operator for Fluid Dynamics
arXiv:2608. 14120v1 Announce Type: cross Abstract: Lagrangian modeling is vital to fluid dynamics, as it characterizes particle transport and complements the Eulerian description.
arXiv AI
5d ago
A Four-Axis Trustworthiness Benchmark for LLM-as-Judge in Principle-Based Regulation
arXiv:2608. 14329v1 Announce Type: cross Abstract: Principle-based regulation, with evaluative standards such as "fair, clear, and not misleading" or "deliver good outcomes", cannot be reduced to binary predicates, and LLM-as-judge is increasingly used as the substitute.
arXiv AI
5d ago
BUZZY: Contrastive Scoring to Mitigate Text-Induced Bias in Multimodal Multiple-Choice QA
arXiv:2603. 28026v2 Announce Type: replace Abstract: Multimodal multiple-choice question answering (MCQA) provides a standardized and objectively measurable setting for evaluating vision-language models (VLMs).
arXiv AI
5d ago
OTIS: Learning High-Quality Time Series Features With Tiny Encoders
arXiv:2410. 07299v3 Announce Type: replace-cross Abstract: We introduce OTIS, an open time series encoder that yields high-quality time series features for downstream deployment on any system, including resource-constrained wearables and industrial sensors.
arXiv AI
5d ago
Fine-grained Claim-level RAG Benchmark for Law
arXiv:2605. 21071v4 Announce Type: replace-cross Abstract: The rapid progress of large language models (LLMs) is shifting semantic search toward a question-answering paradigm, where users ask questions and LLMs generate responses.
arXiv Machine Learning
5d ago
Hard Cases, Bad Labels: Testing Error Exposure and Error Location in Uncertainty Sampling Under Bounded Label Noise
arXiv:2608. 13601v1 Announce Type: new Abstract: Active learning can reduce labeling cost by selecting informative examples, but the most uncertain examples may also be the hardest to label correctly.
arXiv Machine Learning
5d ago
Dynamic Multi-Depot Vehicle Routing with Online Requests: Event-Driven Transformer--DRL and Rolling-Horizon Benchmarking
arXiv:2608. 13799v1 Announce Type: new Abstract: This paper presents an event-driven learning and benchmarking framework for the Dynamic Multi-Depot Vehicle Routing Problem with progressively revealed requests and evolving vehicle states.
arXiv Machine Learning
5d ago
Model-agnostic Retrieval-Augmented Extended Forecasting for time series
arXiv:2608. 14054v1 Announce Type: new Abstract: Time series forecasting with pretrained foundation models has demonstrated strong zero-shot capabilities.
arXiv Machine Learning
5d ago
BCIJelly: An integrated ecosystem for brain-computer interface research
arXiv:2608. 13576v1 Announce Type: cross Abstract: Brain-computer interface (BCI) research relies on multistage computational pipelines, yet progress remains constrained by fragmented data formats, heterogeneous decoder implementations and hardware-specific deployment toolchains, and researchers lack an integrated workflow.
arXiv Machine Learning
5d ago
SALSA-V: Shortcut-Augmented Long-form Synchronized Audio from Videos
arXiv:2510. 02916v2 Announce Type: replace-cross Abstract: We propose SALSA-V, a multimodal video-to-audio generation model capable of synthesizing highly synchronized, high-fidelity long-form audio from silent video content.
arXiv AI
5d ago
Training-Free Knowledge Transfer Across Model Scales through Activation-Guided Pruning
arXiv:2608. 13596v1 Announce Type: cross Abstract: Heterogeneous model fusion seeks to combine models that differ in tasks, initializations, architectures, or scales.
arXiv AI
5d ago
AI Research Preference Models
arXiv:2608. 13940v1 Announce Type: new Abstract: AI research agents (AIRA) can now propose, implement, and evaluate their own machine learning experiments, but progress on frontier tasks is throttled by cost: a candidate solution can be written in minutes, whereas evaluating it can take hours to days of GPU time.
Hugging Face Trending Papers
5d ago
Structured Prediction for Scalable Spreadsheet Table Understanding: From Cell Types to Table Ranges (Extended Version)
Spreadsheets are a primary medium for publishing tabular data, yet automatically extracting structured content from them remains difficult due to heterogeneous layouts, diverse file formats, and inconsistent organizational conventions. We address two core tasks in spreadsheet understanding: Cell-Type Classification (CTC), which assigns roles to cells, and Table Detection (TD), which identifies table bounding boxes within sheets.
Hugging Face Trending Papers
6d ago
$R^3$-Bench: LLMs Struggle with Resource-Rational Reasoning under Shared Budgets
In cognitive science, resource rationality asks how an agent should allocate limited computation to maximize expected value. Most reasoning and agent benchmarks use independent per-task budgets; exist...
Hugging Face Trending Papers
6d ago
AdROD: HyperNetwork-based Adversarially Robust Object Detection for Autonomous Driving
Camera-based object detectors are vulnerable to physical adversarial attacks designed to suppress detections. While adversarial training and input purification offer some protection, they often overfit to specific attack distributions and fail on adaptive adversaries.