The paper introduces a new structural merge tool that ensures parsability and universality in comparison to existing tools, resulting in fewer incorrect merge results.

This paper presents Vivace, a serverless system for exact temporal OLAP over interval histories, which addresses the issues of incomplete data and incorrect answers in serverless functions.

ResMerge proposes a residual-based spectral merging framework that improves the combination of multiple reinforcement learning (RL) expert models by stabilizing the aggregation process using a residua…

OxyMake is a content-addressed cache key workflow engine that replaces mtime with a BLAKE3 hash for caching decisions, eliminating spurious re-runs and traveling across machines and shared caches.

The paper introduces TrojanMerge, a framework demonstrating that model merging can be exploited to systematically compromise the safety alignment of multiple individually safe LLMs.

This paper introduces Stale Synchronous Parallel mode of execution for parallel sparse triangular linear system solve and presents a scheduler that achieves geometric-mean speed-ups of 7-30% over Grow…

RogueMerge introduces a unified framework to robustly attack LLM model merging by addressing the challenges of autoregressive decoding, unknown merging configurations, and prompt generalization, signi…

A simple online algorithm is presented for the stacking problem to avoid shifts with a sufficient condition involving stacking area dimension, load/unload points, and maximum items.

The paper introduces TimeSage-MT, a comprehensive multi-turn benchmark designed to rigorously test an LLM agent's ability to perform complex, evolving time series analysis, revealing critical gaps in…

The paper proposes TDPM, a time-aware diffusion model for generative recommendation, which significantly improves recommendation accuracy by explicitly modeling the non-stationary, time-evolving natur…

The paper establishes a unified framework for timed opacity by introducing a universal observation model and defining evolution-based timed opacity, proving its relationship to existing opacity defini…

This paper proposes Yi, a system for efficient and effective in-place updates in large-scale vector indexing, achieving higher update and search throughput than state-of-the-art methods.

This paper evaluates the performance of large language models on popular benchmarks and finds that only a small percentage of the performant implementations are significantly faster than canonical sol…

CHRONOS is a novel three-layer architecture designed to address coupled failures in temporal data marketplaces by integrating temporal decay, changepoint-aware pricing, and differential privacy for ro…

This paper proposes a taxonomy-guided evaluation protocol for temporal fidelity in synthetic sequential tabular data, measuring timestamp validity, cross-sectional structure, within-entity dynamics, a…

The paper proposes a flexible meta-programming framework to declaratively operationalize and explore varied temporal logics, such as TEL, MEL, and DEL, within standard Answer Set Programming systems.

This paper introduces model merging as a training-free strategy for designing a single retrieval model that operates across both ad-hoc and conversational settings, improving ad-hoc search capabilitie…

The paper proposes a deterministic, version-aware aggregation method that significantly outperforms existing LLM-based systems for resolving memory conflicts in fact consolidation tasks.