arXiv AI
Jun 30
How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models
arXiv:2604. 04385v5 Announce Type: replace-cross Abstract: We localize the policy routing mechanism in alignment-trained language models.
Benchmarks and evaluation
Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv AI
Jun 30
Evidence-Based Text-Conditioned 3D CT Synthesis for Ovarian Cancer
arXiv:2606. 28980v1 Announce Type: cross Abstract: Ovarian cancer is frequently diagnosed at an advanced stage, making preoperative contrast-enhanced computed tomography (CT) central to staging and surgical planning; yet the scarcity of annotated imaging data, compounded by privacy regulations, limits the development of generalizable computational models in this domain.
arXiv AI
Jun 30
MuseBench: Benchmarking Intent-Level Audiovisual Arts Understanding in MLLMs
arXiv:2606. 30026v1 Announce Type: cross Abstract: Audiovisual arts encompass diverse creative disciplines, including cinema, visual arts, stage performance, and game design, where artistic meaning arises from deliberate combinations of visual, auditory, and narrative elements (e.
arXiv AI
Jun 30
Hyper-Network Neural Functional Maps for Unsupervised Robust 3D Shape Matching
arXiv:2606. 30131v1 Announce Type: cross Abstract: Functional maps are the cornerstone of recent non-rigid 3D shape matching methods due to their efficiency and performance.
arXiv Machine Learning
Jun 30
Local-Minima-Preserving Continuous Relaxation of Ising Problems
arXiv:2606. 30333v1 Announce Type: cross Abstract: The generalized Ising problem captures a broad spectrum of hard combinatorial problems, including MAX-CUT, Number Partitioning (NPP), and Maximum Independent Set.
arXiv AI
Jun 30
Defeat Devices in AI Systems
arXiv:2606. 28863v1 Announce Type: cross Abstract: AI systems increasingly exhibit behavior that differs systematically between evaluation and deployment contexts.
arXiv AI
Jun 30
Query-Aware Spreading Activation for Multi-Hop Retrieval over Knowledge Graphs
arXiv:2606. 30133v1 Announce Type: cross Abstract: Retrieval-augmented generation built on knowledge graphs (Graph RAG) outperforms flat passage retrieval on multi-hop question answering by leveraging graph structure.
arXiv AI
Jun 30
Beyond Drug Discovery: The Nanotechnology Molecular Optimization (NMO) Benchmark
arXiv:2606. 30170v1 Announce Type: cross Abstract: Generative molecular design is shaped by simple proxy benchmarks for drug-like properties and models pretrained on large pharmaceutical datasets.
arXiv AI
Jun 30
Physically-Constrained Harmonic Separation for Robust Heart and Respiratory Rate Estimation from Wrist Photoplethysmography
arXiv:2606. 30156v1 Announce Type: cross Abstract: Wrist-worn photoplethysmography (PPG) enables continuous monitoring of cardiopulmonary physiology, but reliable heart rate (HR) and respiratory rate (RR) estimation in free-living conditions remains challenging due to non-stationary motion artifacts that spectrally overlap with physiological dynamics.
arXiv AI
Jun 30
Physics-Informed Distillation of Diffusion Models for PDE-Constrained Generation
arXiv:2505. 22391v2 Announce Type: replace-cross Abstract: Modeling physical systems in a generative manner offers several advantages, including the ability to handle partial observations, generate diverse solutions, and address both forward and inverse problems.
arXiv AI
Jun 30
Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question Answering
arXiv:2502. 11491v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown remarkable capabilities in natural language processing.
arXiv AI
Jun 30
When Web Agents Finish but Still Fail: Reproducible Triggers and Trace Diagnostics for Parallel Web Exploration
arXiv:2606. 20724v2 Announce Type: replace Abstract: Long-horizon web agents often fail in ways hidden by final-answer evaluation: they may visit useful pages, produce a well-formed answer, and terminate confidently while still missing fields, over-including unsupported items, or relying on stale evidence.
arXiv AI
Jun 30
CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents
arXiv:2511. 02734v3 Announce Type: replace Abstract: Current evaluations of Large Language Model (LLM) agents primarily emphasize task completion, often overlooking resource efficiency and adaptability.
arXiv AI
Jun 30
SciVisAgentBench: A Benchmark for Evaluating Scientific Data Analysis and Visualization Agents
arXiv:2603. 29139v2 Announce Type: replace Abstract: Recent advances in large language models (LLMs) have enabled agentic systems to translate natural-language intent into executable scientific visualization (SciVis) tasks.
arXiv AI
Jun 30
TraceLab: Characterizing Coding Agent Workloads for LLM Serving
arXiv:2606. 30560v1 Announce Type: cross Abstract: Coding agents are rapidly becoming a major application of agentic LLMs, but serving them efficiently remains challenging.
arXiv AI
Jun 30
LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals
arXiv:2411. 10109v3 Announce Type: replace Abstract: Machine learning can predict human behavior well when substantial structured data are available for well-defined outcomes.
arXiv AI
Jun 30
The Verbose Context Problem in Medical Records
arXiv:2606. 29503v1 Announce Type: cross Abstract: The verbose context problem occurs when structured concepts have token-inefficient textual representations.
arXiv AI
Jun 30
SAKE: Software Architectural Knowledge Evaluation Benchmark for Large Language Models
arXiv:2606. 29520v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used as assistants across the software development lifecycle, yet their ability to reason about software architecture remains largely unmeasured.
arXiv AI
Jun 30
Pondering the Way: Spatial-perceiving World Action Model for Embodied Navigation
arXiv:2606. 29908v1 Announce Type: cross Abstract: Existing world model-based planners for visual navigation typically follow a verification-centric paradigm, decoupling goal intent from trajectory synthesis.
arXiv AI
Jun 30
Closing the Activation-Cone Blind Spot: Response-Time Probing and Unified Defense
arXiv:2606. 29441v1 Announce Type: cross Abstract: Inference-time safety methods for large language models have proliferated, yet no systematic comparison exists.