Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2608.29291v1 Announce Type: new Abstract: Unified multimodal models jointly support understanding and generation, but incur substantial redundant computation across tokens, layers, and generati...
arXiv:2608.29264v1 Announce Type: new Abstract: Diffusion-based visual generative models deliver strong image and video synthesis quality but incur high inference costs because sequential samplers re...
The paper investigates how making responsible‑AI evaluations more efficient—through batching, quantization, and benchmark reduction—affects the stability of conclusions drawn about model behavior. By testing three dense and mixture‑of‑experts models on the BBQ and BBQ‑V datasets under seven different conditions, the authors compare accuracy, bias, reasoning quality, subgroup performance, subset‑membership stability, runtime, and GPU energy consumption against a full‑benchmark BF16 baseline. Findings show that larger batching preserves accuracy and reduces energy in most settings, INT8 largely maintains quality but can increase energy use, INT4 introduces larger, context‑dependent changes, and reduced benchmarks save resources but are highly sensitive to which items are retained, underscoring that efficient evaluation must be validated against the benchmark’s intended conclusions.
arXiv:2608.29030v1 Announce Type: new Abstract: In-context watermarking (ICW) prepends an instruction to a query asking the model to embed a statistically detectable signal in its response. It thus e...
arXiv:2607.14088v2 Announce Type: replace Abstract: Video generation models typically rely on 3D-VAEs trained for pixel-level reconstruction, whose latent spaces may underrepresent semantic structure...
arXiv:2606.10537v2 Announce Type: replace Abstract: Diffusion large language models (dLLMs) re-encode the entire prefix at every denoising step, causing recomputation that scales quadratically with...
arXiv:2608.30034v1 Announce Type: new Abstract: Two-stage vision pipelines often place an enhancement network before a task network, on the assumption that a cleaner input produces a better output. W...
arXiv:2608.29127v1 Announce Type: new Abstract: We propose a scalable, validity-oriented pipeline for evaluating biomedical LLM judges when high-quality human judgments are scarce. First, we augment...
arXiv:2608.21719v1 Announce Type: cross Abstract: AI inference clusters are increasingly constrained by instantaneous power, not just energy: grid operators condition new capacity on demand response,...
arXiv:2604.09166v3 Announce Type: replace Abstract: Anomaly detection (AD) in chemical processes based on deep learning offers significant opportunities but requires large, diverse, and well-annotate...
arXiv:2608.30510v1 Announce Type: cross Abstract: For provenance research and art market studies, auction catalogs are an essential resource to trace specific objects over time and space. While histo...
arXiv:2608.30122v1 Announce Type: cross Abstract: Vision-language-action (VLA) driving methods increasingly combine multi-trajectory imitation learning with group-relative policy optimization (GRPO),...
arXiv:2608.30295v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated strong capabilities in handling long-context tasks, but processing such long contexts remains challeng...
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:2608.29623v1 Announce Type: cross Abstract: Recent advances in large reasoning models (LRMs) have shown strong performance on complex problems through long chain-of-thought (Long CoT) reasoning...
arXiv:2608.30935v1 Announce Type: cross Abstract: Embodied navigation requires agents to translate heterogeneous goals and visual observations into actions across tasks, environments, and robot embod...
arXiv:2608.29472v1 Announce Type: cross Abstract: Knowledge distillation trains a small student model to reproduce the outputs of a large teacher model, and its progress is typically monitored throug...
arXiv:2608.29563v1 Announce Type: cross Abstract: School coaches prepare for opponents with game film and intuition. The analytics tools of professional teams stay out of reach. We ask how far public...
The paper introduces CFKD-AFN, a cross‑fidelity knowledge distillation and adaptive fusion network that uses abundant low‑fidelity simulation data to improve personalized treatment outcome predictions from scarce high‑fidelity trial data. The dual‑channel distillation module extracts complementary knowledge from the low‑fidelity model, while an attention‑guided fusion module adaptively integrates multi‑source information. Experiments on chronic obstructive pulmonary disease data demonstrate significant reductions in mean squared error (6.67%–74.55%) and mean absolute percentage error (1.43%–51.54%) compared to competing methods, and the framework can be extended to an interpretable variant for feature‑attribution analysis.
The paper introduces FAB, an attack that uses meta‑learning to embed dormant adversarial behaviors into large language models (LLMs). These behaviors remain inactive until the model is finetuned by downstream users, at which point the model can exhibit unwanted actions such as unsolicited advertising, jailbreakability, or over‑refusal. FAB is shown to be effective across multiple LLMs and resilient to various finetuning settings.