arXiv:2605.26266v1 Announce Type: new Abstract: Chunk-wise autoregressive video diffusion models rely on a KV cache of previously generated chunks to avoid redundant computation, but this cache quickly becomes a memory bottleneck as videos grow longer. Methods that quantize the KV…
arXiv:2510.14542v2 Announce Type: replace-cross Abstract: We study deep state-space models (Deep SSMs) that contain linear quadratic-output (LQO) systems as internal blocks and present a compression method with a provable output error guarantee. We first derive an upper bound on the…
arXiv:2605.26282v1 Announce Type: new Abstract: Model-based reinforcement learning (RL) can be effectively supported at scale through the use of world models. However, in practice, scaling such approaches remains fundamentally limited. A commonly recognized challenge is model bias and error compounding,…
arXiv:2601.12809v2 Announce Type: replace-cross Abstract: Spatial understanding remains a key challenge in vision-language models. Yet it is still unclear whether such understanding is truly acquired, and if so, through what mechanisms. We present a controllable 1D image-text testbed to probe…
arXiv:2605.26285v1 Announce Type: new Abstract: This work addresses the problem of learning the dynamics of high-dimensional probability densities over time using unlabeled samples, without assuming access to trajectory information. We introduce two-parameter flows that learn only sampling-time transports from a…
arXiv:2603.15500v2 Announce Type: replace-cross Abstract: LLMs often exhibit Aha moments such as self-correction after tokens like “Wait,” yet the underlying mechanism remains unclear. Standard LLMs collapse mainly through silent divergence, where trajectories drift from the correct answer yet remain locally…
arXiv:2605.26289v1 Announce Type: new Abstract: Multi-agent tool calling is becoming the dominant interaction pattern for LLM-based systems, yet existing inference frameworks treat each tool call as an independent request, re-processing the entire conversation from scratch even though 85-95% of the…
arXiv:2605.07632v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used as surrogates for human participants, but it remains unclear which models best capture human behavior and why. To address this, we introduce Psych-201, a novel dataset that enables…
arXiv:2605.26290v1 Announce Type: new Abstract: Temporal signed networks (TSNs) model the time evolution of cooperative and adversarial relationships that arise in applications such as social media analysis, trust and reputation systems, and financial transaction networks. While graph neural networks (GNNs)…
arXiv:2506.09398v3 Announce Type: replace Abstract: We consider the task of predicting Hamiltonian matrices to accelerate electronic structure calculations, which plays an important role in physics, chemistry, and materials science. Motivated by the inherent relationship between the off-diagonal blocks of the…
