Human mobility data are fundamental to Web-based location services and broader urban applications, and mobility generation provides synthetic trajectories when real data are costly or inaccessible. Although recent mobility generators have incorporated collective mobility patterns, they primarily focus on individual tra...
Bo Liu, Tong Li, Jia-Peng Zhang et al.· 0 citations
Agents are starting to sell to other agents. Seller agents write the listings of tools, services and products, and buyer agents read these listings when they choose what to use. We show that seller agents told only to be selected more often practice generative engine optimization on their own, and that this distorts th...
Zhenwei Tang, Di Bai, Jintao Liu et al.· 0 citations
Large Language Model inference over long contexts is increasingly bottlenecked by the cost of attending to a growing Key-Value (KV) cache. Sparse attention reduces this cost by accessing only a fraction of the cache, but existing methods face a trade-off between deterministic retrieval, which captures high-scoring toke...
Sahil Joshi, Prithvi Dixit, Aryan Katiyar et al.· 0 citations
This work introduces DIVE, a benchmark for evaluating full-duplex interaction with visual engagement under continuous and realistic multimodal streams and evaluates representative real-time models using response quality, window response rates, and reaction latency.
Head-dimension compression can reduce the memory required by the key-value (KV) cache, but existing methods often reconstruct full-dimensional representations during inference, adding significant decoding FLOPs overhead. We formalize the design considerations for converting pretrained attention into a natively reduced-...
Irene Tenison, Abdulrahman Alabdulkareem, D. Weidele et al.· 0 citations
FALCA is proposed, a falsification-aware framework that formulates deep search as a propose-falsify process and improves long-horizon deep search performance over backbone and harness ablations, while reducing confirmation bias and error accumulation through more effective falsification and research-state revision.
Zi-Jun Dou, Kun Luo, Chao-Fan Li et al.· 0 citations
Spatial reasoning asks a model to work out where objects are in 3D space, how they relate to one another, and how they move. Agentic VLMs have recently brought large improvements on such tasks by letting the model actively gather evidence with 3D perception tools instead of answering in a single pass. Even so, on many...
Rui Gong, Ruoyu Wang, Yalun Dai et al.· 0 citations
It is proposed that factual sycophancy arises when in-context updating gives a user's assertion excessive weight relative to its evidence, a trade-off that calls for evaluations measuring both behaviors and mitigations that decouple them.
Multimodal large language models (MLLMs) have substantially advanced chart understanding and reasoning, yet their performance remains highly uneven across chart types. While modern MLLMs perform well on common charts, their accuracy drops sharply on long-tail charts with diverse visual structures and reasoning requirem...
Recursive self-improvement (RSI) of agent harnesses has emerged as an effective approach to enhancing the capabilities of large language model (LLM) agents. By searching the harness space for a specific LLM on a given dataset, RSI can discover a harness tailored to the capabilities and behavioral characteristics of tha...
Safe autonomous navigation of UASs requires tactical deconfliction to address conflicts that strategic coordination cannot prevent. This task is challenging under partial observability, when sensor or traffic data are missing, delayed, or degraded. Geometry-based methods can offer separation assurances but face limitat...
Christopher Conrad, Deepak Panda, Weisi Guo et al.· 0 citations
Spiking Neural Networks (SNNs) have shown great potential for low-power neuromorphic computing due to their event-driven processing and spatiotemporal sparsity, but they remain vulnerable to input perturbations, hardware-intrinsic noise, and adversarial attacks in real-world deployment. We attribute this vulnerability...
Yu-Ling Zha, Wang Fan, Ying Dai et al.· 0 citations
