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.

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.

This survey analyzes the field of On-device Learning (ODL) for TinyML by categorizing existing works based on how they address various types of post-deployment distribution changes.

The paper proposes Joint Neighborhood Optimization (JNO), a novel knowledge-editing framework that jointly addresses the coupled pressures of desirable knowledge propagation and unintended knowledge l…

This paper introduces PatchOptic, an interface for managing valid local updates in agentic workflows over shared state using optics and verified patches.

This paper introduces Stigmergic Graph Memory (SGM), a method to improve warehouse throughput in many-to-many Multi-Agent Pickup and Delivery (MAPD) by using a bounded, decaying memory layer to record…

Phoenix is a multi-agent system that uses seven safety controls and a test evaluation strategy to resolve GitHub issues, achieving 75% oracle-resolution with no regressions on a curated benchmark and…

The paper proposes a decentralized, witnessing-zone architecture that enhances Proof-of-Location (PoL) to provide robust, auditable evidence of physical events, thereby improving sensor data trustwort…

The paper proposes a DAO and blockchain-based framework to decentralize and incentivize community participation in facility management, demonstrating its potential for collective building upkeep.

This paper introduces MM-IssueLoc, a benchmark and evaluation protocol for repository-level issue localization with visual evidence.

The paper presents BigBag, an agentic framework that generates reusable fixing transformations for third-party library breaking API changes, achieving a compilable transformation rate of 94.3% and a f…

This paper introduces tap, a file-based collaboration protocol enabling LLM agents from different vendors to collaborate on a shared codebase without shared memory or identical runtimes.

The paper proposes a novel Large Neighborhood Search (LNS) method, incorporating hybrid destroy operators and an exact repair solver, to effectively solve the Capacitated Facility Location Problem wit…

This paper presents a practical pipeline for designing and deploying large-scale Mixed Reality art exhibitions using SLAM-based alignment, and evaluates its impact on technical stability and user expe…

Jailbreak bypasses database engines by reading storage files directly and materializing data as in-memory columnar buffers using LLM-assisted code synthesis.

This paper introduces DiStash, a disaggregated transactional key-value store that enables an application to use a single transaction to manage key-value pairs across different pools of stashes, preven…

The paper proposes using Trusted-Execution Environments (TEEs) to create a scalable, privacy-preserving system where authors can submit cryptographic proofs of correct research replication, thereby ad…