This paper systematically identifies long-term operational risks associated with smart household appliances, using the smart fridge as a case study, and finds that even basic functions are vulnerable…

The paper introduces SpatialBench-Long, a comprehensive benchmark designed to test AI agents' ability to perform end-to-end scientific reasoning and derive biological claims from complex, raw spatial…

The paper proposes Periodic RoPE (P-RoPE) combined with a dual-layer attention mechanism to overcome the positional encoding limitations of LLMs, enabling theoretically infinite context understanding.

This paper shows that for every graph, there exist a certain number of vertex-disjoint cycles of different lengths, or a smaller set of vertices such that the graph without these vertices has fewer cy…

This paper completely characterizes cyclic equalizability for two words over any finite alphabet by proving that the words must share the same Parikh vector.

The paper introduces EvoXXLTraffic, an ultra-large, sensor-evolving dataset that simulates real-world road network growth, demonstrating that existing state-of-the-art traffic forecasting models fail…

This paper proposes LongE2V, a method for high-quality video recovery from sparse event streams using pre-trained video diffusion priors.

LongAttnComp introduces a novel, two-stage fine-tuning framework for context compression that significantly improves long-context reasoning performance, matching or exceeding full-context accuracy on…

This paper analyzes the synchronization of power usage in large-scale AI training facilities and identifies the coupling channel in load-dependent throttling.

The paper proposes a Cycle-Space Detector (CSD) that uses network topology constraints to effectively detect stealthy, data-driven False Data Injection Attacks (FDIA) that exploit the null space of me…

The paper introduces LongDS, a new benchmark for long-horizon, multi-turn data analysis, demonstrating that current AI agents struggle significantly with maintaining and updating complex analytical st…

This paper studies a random compositional model for the growth of affine regions in deep piecewise-linear networks and proves the existence of a submultiplicative pressure for the number of affine pie…

The paper provides new longest chordless paths, called snakes, in hypercube graphs $Q_n$ for dimensions 9 to 13, improving the lower bound on $a(n)$.

This paper proposes a hierarchical analytical framework to characterize region-level latency differences in Low-Earth orbit satellite Internet using Starlink RTT measurements.

LongLive-RAG proposes a novel Retrieval-Augmented Generation (RAG) framework to stabilize and improve the quality of long-horizon video generation by treating the entire generated history as a searcha…

This paper analyzes the Metabolic Multi-Agent Optimizer (MMAO) framework at a high level, establishing properties and identifying behavioral regimes.

The paper introduces TaskWeave, a hierarchical agentic framework that successfully simulates long-horizon organizational dynamics by treating coordination as a memory-centered problem, demonstrating t…