arXiv:2512.07419v2 Announce Type: replace Abstract: Mixed-Precision Quantization (MPQ) liberates Deep Neural Networks (DNNs) from the Out-Of-Memory (OOM) bottleneck and has garnered increasing research attention. However, conventional methods either rely on costly differentiable optimization search, which is neither efficient nor flexible,…
arXiv:2602.09980v2 Announce Type: replace Abstract: Standard Physics-Informed Neural Networks (PINNs) often face challenges when modeling parameterized dynamical systems with sharp regime transitions, such as bifurcations. In these scenarios, the continuous mapping from parameters to solutions can result in spectral bias…
arXiv:2505.23648v3 Announce Type: replace Abstract: Modern language models generate chain-of-thought traces by autoregressively sampling tokens from a finite vocabulary. While this discrete sampling has achieved remarkable success, conducting chain-of-thought with continuously-valued tokens (CoT2) offers a richer and more expressive alternative.…
arXiv:2509.11612v2 Announce Type: replace Abstract: Reservoir is an efficient network for time series processing. It is well known that network structure is one of the determinants of its performance. However, the topology structure of reservoirs, as well as their performance,…
arXiv:2602.24007v2 Announce Type: replace-cross Abstract: Protein function relies on dynamic conformational ensembles, yet current generative models like AlphaFold3 often fail to produce ensembles that match experimental data. Recent experiment-guided generators attempt to address this by steering the reverse diffusion process.…
arXiv:2603.05504v1 Announce Type: cross Abstract: Scaling imitation learning is fundamentally constrained by the efficiency of data collection. While handheld interfaces have emerged as a scalable solution for in-the-wild data acquisition, they predominantly operate in an open-loop manner: operators blindly collect…
arXiv:2603.04431v1 Announce Type: new Abstract: Physical fields are typically observed only at sparse, time-varying sensor locations, making forecasting and reconstruction ill-posed and uncertainty-critical. We present SOLID, a mask-conditioned diffusion framework that learns spatiotemporal dynamics from sparse observations alone: training and…
arXiv:2603.04428v1 Announce Type: new Abstract: Multi-agent LLM systems on edge devices face a memory management problem: device RAM is too small to hold every agent’s KV cache simultaneously. On Apple M4 Pro with 10.2 GB of cache budget, only 3…
arXiv:2603.04430v1 Announce Type: new Abstract: We introduce Flowers, a neural architecture for learning PDE solution operators built entirely from multihead warps. Aside from pointwise channel mixing and a multiscale scaffold, Flowers use no Fourier multipliers, no dot-product attention, and no…
arXiv:2603.04427v1 Announce Type: new Abstract: Standard transformer attention uses identical dimensionality for queries, keys, and values ($d_q = d_k = d_v = dmodel$). Our insight is that these components serve fundamentally different roles, and this symmetry is unnecessary. Queries and…
