arXiv:2605.07505v1 Announce Type: cross Abstract: Developing lightweight, on-device vision-language GUI agents is essential for efficient cross-platform automated interaction. However, current on-device agents are constrained by limited model capacity, and further performance improvements remain urgently needed. Traditional Supervised Fine-Tuning (SFT) for…
arXiv:2605.06755v1 Announce Type: new Abstract: Reinforcement learning is widely used to improve the reasoning ability of large language models, especially when answers can be automatically checked. Standard GRPO-style training updates the model using only the current step, while full multi-step…
arXiv:2605.07746v1 Announce Type: cross Abstract: High-dimensional count data arise in applications such as single-cell RNA sequencing and neural spike trains, where mapping between distributions across successive batches or time points form critical components of data analysis. The recent success of…
arXiv:2605.06756v1 Announce Type: new Abstract: Real-time supervisory control of thermal energy distribution systems requires digital twins that are accurate, interpretable, and uncertainty-aware, yet remain data and computationally efficient. High-fidelity simulations alone are costly, while purely data-driven surrogates often lack robustness.…
arXiv:2605.07971v1 Announce Type: cross Abstract: We introduce Discrete Voxel Diffusion (DVD), a discrete diffusion framework to generate, assess, and edit sparse voxels for SLat (Structured LATent) based 3D generative pipelines. Although discrete diffusion has not generally displaced continuous diffusion in…
arXiv:2605.06763v1 Announce Type: new Abstract: Sparse attention improves LLM inference efficiency by selecting a subset of key-value entries, but at the cost of potential accuracy degradation. In particular, omitting critical KV entries can induce substantial errors in model outputs. Existing…
arXiv:2602.17251v2 Announce Type: replace Abstract: Electroencephalography (EEG) foundation models (EFMs) have shown strong potential for transferable representation learning, yet their adaptation in realistic settings remains challenging when only a few labeled subjects are available. We show that this challenge stems…
arXiv:2605.02948v2 Announce Type: replace Abstract: Diffusion-based talking head generation has achieved remarkable visual quality, yet scaling it to long-term videos remains challenging. The widely adopted chunk-wise paradigm introduces two fundamental failures: (1) temporal-spatial misalignment between static identity references and dynamic…
arXiv:2506.23875v4 Announce Type: replace Abstract: Sequential computation via autoregressive generation can make difficult tasks learnable, but the generation order of intermediate states strongly affects whether training succeeds. We address the problem of discovering a learning-friendly target order automatically, rather than…
arXiv:2512.23770v3 Announce Type: replace Abstract: In safety-critical domains, reinforcement learning (RL) agents must often satisfy strict, zero-cost safety constraints while accomplishing tasks. Existing model-free methods frequently either fail to achieve near-zero safety violations or become overly conservative. We introduce Safety-Biased…
