Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2609.14815v1 Announce Type: cross Abstract: This paper introduces a novel framework for Regularized Multivariate Functional Principal Component Analysis (ReMFPCA) via Functional Singular Value...
arXiv:2609.15743v1 Announce Type: new Abstract: Automatic speech recognition (ASR) systems, trained on paired speech-text data, have been improved by leveraging language models (LMs) trained on text-...
arXiv:2609.14246v1 Announce Type: cross Abstract: In wireless federated learning (FL), data heterogeneity and multiple local updates induce client drift, degrading model convergence. It is further af...
arXiv:2609.14261v1 Announce Type: cross Abstract: Recent robot learning paradigms increasingly rely on large offline datasets of robotic interactions to train control policies. Expressive generative...
arXiv:2609.14735v1 Announce Type: cross Abstract: Deep Learning (DL)-based channel estimation has shown high accuracy and low latency in terrestrial 5G NR, but Low Earth Orbit (LEO) Non-Terrestrial N...
arXiv:2609.13636v1 Announce Type: cross Abstract: Privacy-preserving inference via Torus Fully Homomorphic Encryption (TFHE) provides strong protection for sensitive data in outsourced deep learning...
arXiv:2609.14146v1 Announce Type: cross Abstract: Vision-language-action (VLA) deployment can reduce inference latency while changing closed-loop task behavior. We evaluate HuggingFaceVLA/smolvla_lib...
arXiv:2609.13260v1 Announce Type: cross Abstract: This paper proposes SpecAugment-Patch Merging, a simple yet effective method to accelerate Audio Spectrogram Transformer (AST) training. We first app...
arXiv:2609.13271v1 Announce Type: cross Abstract: Medical image segmentation needs diverse training data, but hospitals hold complementary scans they cannot share for privacy and regulatory reasons....
The paper introduces Verifier-Gated Multi-Expert On-Policy Distillation (VG‑OPD), a method that assigns teacher supervision at the token level based on each expert’s counterfactual gain on a specific answer criterion. VG‑OPD localizes supervision where experts disagree most with the student and weights it by criterion importance, integrating this into a gated KL advantage for reinforcement learning. Applied to scientific reasoning, VG‑OPD achieves top performance on seven benchmarks for 4B and 8B models, outperforming prior multi‑teacher distillation approaches.
arXiv:2609.15177v1 Announce Type: new Abstract: Diffusion language models (dLLMs) promise fast inference by generating multiple tokens in parallel, but suffer severe performance degradation when para...
arXiv:2609.13243v1 Announce Type: cross Abstract: We present GzDRL, a novel single-process reinforcement learning (RL) framework for Gazebo that overcomes longstanding bottlenecks in scalable, reprod...
arXiv:2602.08370v2 Announce Type: replace-cross Abstract: Realizing versatile and human-like performance in high-demand sports like badminton remains a formidable challenge for humanoid robotics. Unl...
The paper introduces WaterKron, a method that integrates two-sided GPTQ with row- and column-dependent waterfilling scales and entropy coding for post‑training quantization. It derives a high‑rate distortion measure relative to the full Hessian, introducing a Kronecker‑Hessian mismatch factor Φ that quantifies the distortion penalty of using a Kronecker approximation. Minimizing Φ leads to a Gaussian covariance‑fitting problem solved via classical flip‑flop updates, yielding a FlipFlop Hessian that empirically improves KL divergence and perplexity compared to other Hessian choices.
arXiv:2605.06165v2 Announce Type: replace Abstract: As the widespread adoption of Large Language Models (LLMs) accelerates, token consumption from intermediate reasoning traces increasingly contribut...
OCT-FedSIR is a reliability‑aware spectral framework designed for federated learning of OCT image classification in the presence of client‑dependent annotation noise and heterogeneous data distributions. It integrates class‑balanced spectral estimation, logit adjustment, complementary spectral descriptors, selective spectral relabeling, and noise‑aware federated optimization. Across 117 experimental conditions on three datasets, OCT‑FedSIR achieved a mean accuracy of 86.73%, outperforming RoFL (79.94%) and FedCorr (78.75%) and successfully identifying and correcting corrupted annotations with high precision.
arXiv:2609.14968v1 Announce Type: new Abstract: Online scheduling of dependency-aware tasks in heterogeneous cloud clusters is a fundamental yet challenging problem due to the complex interplay betwe...
arXiv:2609.14193v1 Announce Type: cross Abstract: On-policy distillation (OPD) has become a standard component of frontier post-training pipelines, yet how much its training data actually contributes...
SynGhost is a novel task‑agnostic backdoor attack that injects invisible syntactic backdoors into pre‑training corpora of language models. It uses an entropy‑based poisoning filter, contrastive learning to select optimal targets, and an awareness module to reduce interference between backdoors, thereby preserving the model’s pre‑training performance. Experiments demonstrate that SynGhost can transfer to multiple downstream tasks and withstand several defense mechanisms such as perplexity checks, fine‑pruning, and the maxEntropy filter.
arXiv:2609.13899v1 Announce Type: cross Abstract: The BabyLM challenge measures how much language a model can learn from developmentally-plausible, child-scale data rather than internet-scale corpora...