Found 247,085 document(s)
Page 75 of 16473
-
We show that adding "catalytic space" (which starts full and must have its original contents restored at the end of computation) provably speeds up time-and-space-bounded computation. In a natural output model, with $O(\...
-
As multimodal agents accumulate experience, their long-term memories contain many similar observations of recurring scenes, actions, and entities. Answer quality depends on the evidence retrieved from these memories into...
-
Recent work shows that attackers can implant dormant malicious behaviors that remain hidden at release but emerge after benign fine-tuning. As foundation models are used as agents, whether dormant poisoning extends to ha...
-
Multi-agent systems (MAS) can outperform individual language-model agents by combining specialized roles, diverse reasoning processes, and collaborative decision-making. However, collaborative MAS training is typically c...
-
Scientific discovery does not follow a single fixed methodology: research methods vary across domains and evolve through experimentation as investigations unfold. Although LLM-guided evolutionary search has advanced auto...
-
Agent systems deployed in dynamic environments continuously update their memories, skills, and runtime configurations, leading to evolving trajectories and challenges for persistent identity authentication. Existing text...
-
Improving every agent in an LLM-based multi-agent system can be prohibitively costly, making it important to identify which agent should be prioritized to achieve the greatest system-level gain with limited resources. Fa...
-
Financial time series exhibit multi-scale, high-noise, and non-stationary volatility dynamics. Decomposition--integration frameworks built on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) h...
-
Effective test-time personalization requires LLM agents to adapt to query-dependent user preferences from lightweight interaction. We study persona selection with binary comparisons between candidate responses as the onl...
-
Stock price forecasting is hindered by the heteroscedastic nature of financial time series, in which turbulent and tranquil regimes alternate. Although the Long Short-Term Memory (LSTM) network is widely used for this ta...
-
This decade-long longitudinal qualitative study follows 31 smartphone users in China across four interview waves (2014-2023) to examine how mobile privacy understanding evolves alongside shifting computing infrastructure...
-
Clinical causal retrieval-augmented generation systems increasingly use knowledge graphs (KGs) mined from notes, yet extracted assertions remain candidates that require audit for patient-level EHR support and direction. ...
-
Macroscopic quantum effects emerge when the coherent behavior of countless microscopic quantum states manifests collectively at a visible scale, as exemplified by the supercurrent carried by innumerable finite-momentum C...
-
Human video demonstrations provide rich manipulation strategies for dexterous manipulation learning. We study a setting in which a fully specified simulated scene is used to generate videos that specify the demonstrated ...
-
In multimodal learning, modality imbalance often lets one modality dominate optimization and keeps the model from fully exploiting cross-modal interactions. Balance-oriented methods such as the Multimodal Competition Reg...