Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2606.22394v3 Announce Type: replace Abstract: Consistency distillation has significantly accelerated diffusion-model inference, but its sampling dynamics remain underexplored. We reveal an asym...
arXiv:2603.20186v2 Announce Type: replace Abstract: In this work, we propose Image-to-Image Rectified Flow Reformulation (I2I-RFR), a practical plug-in reformulation that recasts standard I2I regress...
arXiv:2608.29765v1 Announce Type: new Abstract: Structured pruning uses surrogate objectives because direct task evaluation over every feasible mask is too expensive. Most evaluations report average...
The paper introduces ACTD, an Anchor-Based Cross-Tokenizer Distillation method that aligns vocabularies and sequences to transfer reasoning capabilities from large language models to smaller students. It uses a novel anchor loss with residual regularization to reduce alignment noise and extends the approach to multiple teachers. Experiments on five reasoning benchmarks with three teachers show state‑of‑the‑art results, with the multi‑teacher variant outperforming existing baselines.
arXiv:2508.01684v2 Announce Type: replace Abstract: While diffusion models have demonstrated remarkable progress in 2D image generation and editing, extending these capabilities to 3D editing remains...
arXiv:2512.23649v5 Announce Type: replace-cross Abstract: Humans learn locomotion through visual observation, interpreting visual content first before imitating actions. However, state-of-the-art hum...
The paper introduces CHAP, a personalized generative retrieval framework that aligns query semantics with item representations through a hierarchical semantic alignment module and models user behavior using both discrete Semantic IDs and continuous representations. It also proposes a Residual Cascading Generation mechanism to reduce inference latency by limiting the Transformer decoder to a single pass. Experiments on multiple datasets and online A/B tests show that CHAP outperforms existing methods, demonstrating its practical value.
arXiv:2608.29910v1 Announce Type: new Abstract: Interactive world models extend video generation from offline clip synthesis toward persistent simulation of interactive virtual worlds, enabling appli...
arXiv:2608.30899v1 Announce Type: new Abstract: Most trajectory forecasting models are trained on clean annotated histories, and are often evaluated under the same idealized assumption, although prac...
arXiv:2608.29928v1 Announce Type: new Abstract: State-of-the-art monocular body recovery methods predict mesh vertices and angles on the corresponding kinematic tree, but their outputs lack biomechan...
arXiv:2608.29027v1 Announce Type: new Abstract: Shrimp disease classification has become an urgent issue due to its significant impact on the import-export output of producing countries, particularly...
arXiv:2608.28696v1 Announce Type: new Abstract: Visual in-context learning (ICL) with multimodal large language models (MLLMs) is effective for fine-grained visual classification, but each retrieved...
arXiv:2603.16622v2 Announce Type: replace Abstract: Instead of directly distilling a language model, this study addresses the problem of aligning a base model with a target model in distribution by d...
The paper introduces a lightweight two‑stage system for real‑time video anomaly detection. First, YOLO v11n‑pose detects people and extracts seventeen skeletal keypoints in a single forward pass. Second, each cropped person region is encoded with CLIP ViT‑B/32 and compared via cosine similarity to predefined textual descriptions of anomalous behaviors, removing the need for optical flow, separate pose estimators, or density‑based scoring. Experiments on CUHK Avenue, ShanghaiTech Campus, and a custom indoor dataset achieve about 51 FPS on an NVIDIA Titan XP, a 3.36× speedup over a multi‑feature baseline, while preserving high frame‑level AUROC scores (89.26%, 70.26%, and 84.13%).
arXiv:2608.28730v1 Announce Type: cross Abstract: Latest JPEG restoration systems achieve strong quality with large models, yet often remain too slow and expensive for efficient on-device deployment....
arXiv:2608.31066v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning improves multi-step problem solving, but long reasoning traces inflate inference cost. Token-level CoT compression red...
arXiv:2608.30086v1 Announce Type: cross Abstract: Credit-default prediction is an important task in financial decision making. Traditional methods use fitted classifiers such as logistic regression a...
arXiv:2601.10015v2 Announce Type: replace Abstract: Personalized Federated Learning (PFL) excels at tailoring client-specific models, which is particularly critical for decentralized and heterogeneou...
arXiv:2608.29058v1 Announce Type: new Abstract: Dynamic sparse attention can reduce the quadratic cost of long-context prefilling without changing model weights. MInference assigns each attention hea...
arXiv:2608.29956v1 Announce Type: new Abstract: Large language models often answer complex reasoning questions without revealing intermediate steps, raising whether they reason latently or complete p...