Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
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...
arXiv:2602.15396v2 Announce Type: replace Abstract: Diffusion models often yield highly curved trajectories and noisy score targets due to an uninformative, memoryless forward process that induces in...
arXiv:2606.21562v2 Announce Type: replace Abstract: Transformers are AI's workhorse but their computational cost becomes prohibitive when processing long sequences. We target long-horizon streaming v...
arXiv:2512.04705v3 Announce Type: replace-cross Abstract: The deployment of Early-Exiting Neural Networks (EENNs) on edge accelerators requires optimizing not only the network architecture but also i...
DecomVoxel introduces a guided in‑situ denoising optimization that fuses 3D‑native priors with neural scene reconstruction to improve decompositional scene reconstruction. The method employs an epsilon‑based distillation loss for stable latent refinement and adaptive spatial guidance using occupied and vacant anchors with temporal annealing to reduce hallucinations and spatial drift. Experiments on Replica and ScanNet++ demonstrate that DecomVoxel outperforms state‑of‑the‑art approaches while preserving spatial layout, structural fidelity, and style‑consistent texture, yielding high‑quality textured meshes with clean topology.
Dyna‑DINO introduces a curriculum for Vision Transformer (ViT) knowledge distillation that uses the teacher’s intermediate feature maps as progressively harder targets, enabling a student to build foundational representations before tackling higher‑level abstractions. The approach accelerates convergence and improves performance across multiple tasks: on ImageNet‑100 the distilled ViT‑S reaches 90.1% accuracy (+12.24% over baseline), while on ImageNet‑1K it yields +3.9% and +6.09% gains on Oxford and Paris retrieval, +1.93% on semantic segmentation, and notable classification improvements. Additionally, the curriculum reduces training FLOPs by 25.1% and training time by 21% on ImageNet‑100 through early‑stopping of teacher inference.
RISED introduces a framework that uses rubric-based textual feedback to improve training of a single large language model (LLM) agent across multiple interactive environments. By having an LLM judge tag rollouts with a shared rubric vocabulary, the system guides both online data selection and policy supervision, enabling richer cross‑environment relationships and within‑group reward contrast. Experiments show that RISED achieves the highest mean pass rate and ranks first or second in every individual environment, with rubric analysis revealing behavioural changes behind these gains.
ShatterQuant is a hardware-software co-designed framework that enables mixed-precision quantization within individual tensors by assigning different bit-widths to blocks of a weight projection. It couples precision granularity with processing element configuration, allowing each precision to determine an effective block height. The framework includes a hardware-aware post-training method based on block-level standard deviation and weight sensitivity, a ShatterQuant Transformer Accelerator supporting 1/2/4/8-bit weight precision, precision-dependent PE configuration, block rescaling, and integrated softmax and piecewise-linear nonlinearities, and an evaluation showing 1.5 TOPS, 760 GOPS/$mm^2$ area efficiency, and 2.8 TOPS/W energy efficiency on a TSMC 16nm PDK implementation.