arXiv:2605.04363v1 Announce Type: new
Abstract: TabPFN has recently gained attention as a foundation model for tabular datasets, achieving strong performance by leveraging in-context learning on synthetic data. However, we find that TabPFN is vulnerab…
arXiv:2509.14448v2 Announce Type: replace
Abstract: Benchmarks such as SWE-bench and ARC-AGI demonstrate how shared datasets accelerate progress toward artificial general intelligence (AGI). We introduce VCBench, the first benchmark for predicting fou…
arXiv:2602.10144v2 Announce Type: replace
Abstract: Minimizing the inference cost and latency of foundation models has become a crucial area of research. Optimization approaches include theoretically lossless methods and others without accuracy guaran…
arXiv:2605.04980v1 Announce Type: new
Abstract: Activation-based steering provides control of LLM behavior at inference time, but the dominant paradigm reduces each concept to a single direction whose geometry is left largely unexamined. Rather than s…
arXiv:2511.01553v2 Announce Type: replace
Abstract: AI systems on edge devices require online continual learning — adapting to non-stationary streams and unfamiliar classes without catastrophic forgetting — under strict power constraints. We present…
arXiv:2602.02958v5 Announce Type: replace
Abstract: Despite rapid progress in autoregressive video diffusion, an emerging system algorithm bottleneck limits both deployability and generation capability: KV cache memory. In autoregressive video generat…
arXiv:2605.04993v1 Announce Type: new
Abstract: Accurate forecasting of electric vehicle (EV) charging demand is critical for grid stability, infrastructure planning, and real-time charging optimization. In this work, we study the problem of early pre…
arXiv:2602.02924v2 Announce Type: replace
Abstract: Diffusion policy sampling enables reinforcement learning (RL) to represent multimodal action distributions beyond suboptimal unimodal Gaussian policies. However, existing diffusion-based RL methods p…
arXiv:2602.05890v2 Announce Type: replace
Abstract: Training reinforcement learning (RL) systems in real-world environments remains challenging due to noisy supervision and poor out-of-domain (OOD) generalization, especially in LLM post-training. Rece…
arXiv:2605.05023v1 Announce Type: new
Abstract: Efficient CUDA implementations of attention mechanisms are critical to modern deep learning systems, yet supporting diverse and evolving attention variants remains challenging. Existing frameworks and co…