Featured Papers
Popular high-signal papers with direct links to full protocol pages.
- Spend Less, Fit Better: Budget-Efficient Scaling Law Fitting via Active Experiment Selection
Apr 24, 2026 · Citations: 0
Across a diverse benchmark of scaling-law tasks, our method consistently outperforms classical design-based baselines, and often approaches the performance of fitting on the full experimental set while using only about 10% of the total…
- How Do AI Agents Spend Your Money? Analyzing and Predicting Token Consumption in Agentic Coding Tasks
Apr 24, 2026 · Citations: 0
In this paper, we present the first systematic study of token consumption patterns in agentic coding tasks.
- Representational Harms in LLM-Generated Narratives Against Global Majority Nationalities
Apr 24, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond
Apr 24, 2026 · Citations: 0
Agents that manipulate objects, navigate software, coordinate with others, or design experiments require predictive environment models, yet the term world model carries different meanings across research communities.
- Relaxation-Informed Training of Neural Network Surrogate Models
Apr 24, 2026 · Citations: 0
Experiments on non-convex benchmark functions and a two-stage stochastic programming problem with quantile neural network surrogates demonstrate that the proposed regularizers can reduce MILP solve times by up to four orders of magnitude…
- An Undecidability Proof for the Plan Existence Problem
Apr 24, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Neural Recovery of Historical Lexical Structure in Bantu Languages from Modern Data
Apr 24, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Zero-Shot Morphological Discovery in Low-Resource Bantu Languages via Cross-Lingual Transfer and Unsupervised Clustering
Apr 24, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Aligning Dense Retrievers with LLM Utility via DistillationAligning Dense Retrievers with LLM Utility via Distillation
Apr 24, 2026 · Citations: 0
On the QASPER benchmark, UAE improves retrieval Recall@1 by 30.59%, MAP by 30.16% and Token F1 by 17.3% over the strong semantic baseline BGE-Base.
- Thinking Without Words: Efficient Latent Reasoning with Abstract Chain-of-Thought
Apr 24, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Time-Localized Parametric Decomposition of Respiratory Airflow for Sub-Breath Analysis
Apr 24, 2026 · Citations: 0
Evaluation across 8,276 breaths demonstrates high reconstruction accuracy (mean squared error < 0.001 for four-component models) and robust parameter precision under moderate noise.
- CRAFT: Clustered Regression for Adaptive Filtering of Training data
Apr 24, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.