Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2609.39405v1 Announce Type: new Abstract: Task vectors provide a simple mechanism for composing learned capabilities through model merging. However, the composability of task vectors produced b...
arXiv:2609.39489v1 Announce Type: new Abstract: Sample-level reliability heterogeneity is common in deep time series learning. Standard training pipelines apply a uniform regularization setting to al...
arXiv:2609.39816v1 Announce Type: new Abstract: Fast matrix multiplication saves multiplications through exact cancellation, but rounding sums that mix token rows can leave contributions from later t...
arXiv:2609.39350v1 Announce Type: cross Abstract: As model sizes continue to scale, distributed training has become inevitable. Automatic parallelization techniques can derive efficient training para...
arXiv:2507.12133v2 Announce Type: replace Abstract: Device recognition is vital for security in wireless communication systems, particularly for applications like access control. Radio Frequency Fing...
arXiv:2602.03537v2 Announce Type: replace Abstract: Matryoshka Quantization (MatQuant), Any-Precision-LLM (AP) and AnyBCQ (AB) are recent quantization approaches showing that a single integer-quantiz...
arXiv:2604.08454v2 Announce Type: replace Abstract: Large language models are increasingly deployed in high-stakes domains, where confident yet incorrect inferences may cause severe real-world harm,...
arXiv:2605.12904v2 Announce Type: replace Abstract: Tabular foundation models (TFMs) have emerged as a powerful paradigm for in-context learning on structured data, enabling direct prediction on new...
arXiv:2608.13888v2 Announce Type: replace Abstract: Fashion Outfit Composition (FOC) requires sequentially assembling fashion items into a stylistically cohesive ensemble. Existing works struggle to...
arXiv:2609.19011v2 Announce Type: replace Abstract: Knowledge distillation can copy a deployed model by training a student on its logits or features. The student inherits a watermark only through the...
arXiv:2609.32503v2 Announce Type: replace Abstract: Kolmogorov-Arnold Networks (KANs) are motivated in part by interpretability: their learned edge functions can be inspected, pruned, and reduced to...
arXiv:2607.04171v4 Announce Type: replace-cross Abstract: How can richer training supervision improve robot control while keeping the deployed policy compact? We present XS-VLA, a staged training fra...
arXiv:2607.07494v2 Announce Type: replace-cross Abstract: Gradient communication is a primary scaling bottleneck in large language model (LLM) pretraining. Communicating gradients in low-precision fo...
arXiv:2610.00204v1 Announce Type: new Abstract: Visual-token compression for vision--language models is posed almost entirely as a selection problem: decide which tokens to keep and discard the rest....
arXiv:2610.00757v1 Announce Type: new Abstract: Long-video question answering is limited by the high cost of visual tokens and by the fixed context width of current VLMs. A long-video question may re...
arXiv:2610.00930v1 Announce Type: new Abstract: Post-training quantization for diffusion models increasingly exploits timestep, feature, and layer structure. While recent work has begun incorporating...
arXiv:2610.01098v1 Announce Type: new Abstract: Illusory matches between distinct yet visually similar 3D surfaces--doppelgangers--remain a fundamental obstacle for large-scale, in-the-wild 3D recons...
arXiv:2610.00623v1 Announce Type: new Abstract: Speculative decoding has achieved substantial lossless speedups for LLMs, but remains less effective for large vision-language models (LVLMs), where li...
arXiv:2610.01210v1 Announce Type: new Abstract: Egocentric video has become a primary source of supervision for embodied models, and its value rests on recovering hand motion in world coordinates, wh...
arXiv:2610.01352v1 Announce Type: new Abstract: Open multimodal reasoning models have benefited from large-scale reasoning supervision, yet reliable post-training remains challenging due to uneven da...