The paper introduces SALVE, a method that uses text optimization to uncover and verbalize subliminal learning effects in language models. By optimizing a soft prompt and converting it into a legible text prompt, SALVE can reliably recover the teacher model’s hidden traits that are transmitted through a distillation dataset. The authors demonstrate SALVE’s effectiveness across various scenarios, including mixed datasets, biased teacher activation, and preference‑selected data, thereby providing a tool for detecting hidden influences in model training.
By Nathan Hu, Sanmi Koyejo, Christopher Potts
The paper introduces Adaptive Derivative-Ordered Random Explanation (ADORE), a unified framework that uses first- and second-order derivatives to capture nonlinear feature interactions and feature-sample dynamics. ADORE combines global feature importance with local sample contributions, quantifying both magnitude and direction of feature impact while identifying critical samples. It achieves computational efficiency via randomized SVD and dynamic sparsity detection, outperforming LIME and SHAP across tabular, text, and image data, and is released as an open-source Python package on GitHub.
By Lemen Chao, Ming Lei, Anran Fanga
The paper re‑examines the impact of removing the encoder from Action Chunking Transformers (ACT), a model used for robot manipulation learning. Contrary to the original claim that encoder removal drops success rates from 35% to 2%, the authors find no such dramatic effect in their re‑runs, though minor variations remain uncertain. They attribute discrepancies to training length and checkpoint selection, and note that the encoder’s latent variable offers little reconstruction benefit on the tested benchmark, while its removal speeds up training.
By Bo Kang
arXiv:2609.07595v2 Announce Type: replace-cross
Abstract: The same underlying computational problem is solved across unrelated fields under different names: recursive Bayesian state estimation appear...
By Eryk Kulikowski
arXiv:2609.17230v1 Announce Type: new
Abstract: Streaming 3D reconstruction demands both speed and temporal fidelity, goals that existing methods undermine by updating every Gaussian every frame, eve...
By Idil Sulo, Alexey Supikov, Ilke Demir, Sainan Liu
arXiv:2604.06036v4 Announce Type: replace-cross
Abstract: Continuous inference over concurrent video streams imposes substantial compute and memory demands on vision-language model (VLM) serving. Str...
By Yulin Zou, Wenyan Chen, Yan Chen, Anya Rajan, JooYoung Park, Shivaraman Nitin, Luo Tao, Francisco Romero, Dmitrii Ustiugov
arXiv:2609.16403v1 Announce Type: cross
Abstract: Goldwasser et al. showed that undetectable backdoors can be planted in machine learning models trained with the Random Fourier Features (RFF) algorit...
By Michael Collins, Jada Cumberland, Brianne Dunn, Ross Gore, Samuel Jackson, Sachin Shetty
arXiv:2609.16864v1 Announce Type: cross
Abstract: Vision-language-action (VLA) models have achieved impressive performance in quasi-static manipulation, but struggle in dynamic manipulation tasks bec...
By Zhenyang Feng, Jimin Heo, Erik B. Sudderth, Unnat Jain
arXiv:2609.16937v1 Announce Type: cross
Abstract: On-policy distillation (OPD) has emerged as an effective approach for large language model post-training, yet existing objectives face a trade-off be...
By Shiqi Liu, Zeyu He, Letian Tao, Guojian Zhan, Jiaxin Gao, Feihong Zhang, Jingliang Duan, Wei Xiong, Kehua Sheng, Bo Zhang, Yang Guan, Shengbo Eben Li
arXiv:2607.27245v2 Announce Type: replace-cross
Abstract: Modern policing faces a "visibility paradox" where law enforcement agencies possess petabytes of Body-Worn Camera (BWC) footage that remains...
By Vivek Senthil, Ernest Fokou\'e
arXiv:2609.17509v1 Announce Type: cross
Abstract: Neural audio codecs are a key component in speech language modeling. However, their high frame rates lead to long sequence lengths, increasing comput...
By Thanapat Trachu, Samuele Cornell, William Chen, Shinji Watanabe
arXiv:2609.16059v1 Announce Type: cross
Abstract: Multimodal instruction following (MMIF) is crucial for building generalist agents. However, current training paradigms rely heavily on Supervised Fin...
By Yirong Zeng, Zhang Sai, Yuxian Wang, Yutai Hou, Yufei Liu, Xiao Ding, Bibo Cai
arXiv:2609.17026v1 Announce Type: new
Abstract: Continual learning must balance the learning of new knowledge with the retention of previously learned knowledge to incrementally learn tasks from a da...
By Yunxiang Fu, Meng Lou, Zicheng Liao, Yizhou Yu
The paper evaluates a learned request‑routing policy for disaggregated large‑language‑model serving, where compute‑heavy prefill and memory‑heavy decode stages run on separate GPU pools. Using a discrete‑event simulator and real NVIDIA A40 GPUs, the calibrated router—leveraging prompt length, predicted output length, KV‑cache pressure, and SLO class—outperforms round‑robin, least‑loaded, and length‑based heuristics, achieving the highest mean goodput (0.864) and lowest variance across three mixed, bursty arrival traces. Hardware calibration proves critical, providing a 4.5‑point goodput boost and roughly 40 % of the tail‑latency advantage, and the learned router can match round‑robin performance with one fewer GPU in certain scenarios.
By Srikanta Datta Tumkur, Jay Iyer, Mehar Simhadri, Sai Pavan Kumar, Sai Kapil Kumar, Ramesh Nampelly
arXiv:2604.05012v2 Announce Type: replace-cross
Abstract: Efficient inference with Large Language Models (LLMs) increasingly relies on Key-Value (KV) caches to store previously computed key and value...
By Oteo Mamo, Olga Kogiou, Hyunjin Yi, Weikuan Yu
arXiv:2609.16245v1 Announce Type: new
Abstract: Long-horizon scientific discovery requires agents to alternate between exploration, disciplined execution, and critical reassessment as evidence change...
By Vincent Karpf, Joseph Reth, Eike Gerhardt, Audrey Wang, Anna Butz, Jiehao Xing, Jialing Song, Larry Callahan
arXiv:2609.17474v1 Announce Type: cross
Abstract: Large language model (LLM) distillation aims to transfer the capabilities of a powerful teacher to a smaller student. Direct imitation, however, can...
By Haichen Hu, Yuheng Zhang, David Simchi-Levi
arXiv:2604.18616v2 Announce Type: replace-cross
Abstract: LLM coding agents can generate correct GPU kernels, but their performance still trails expert libraries. Reaching peak throughput requires co...
By Haohui Mai, Xiaoyan Guo, Xiangyun Ding, Daifeng Li, Qiuchu Yu, Chenzhun Guo, Cong Wang, Jiacheng Zhao, Christos Kozyrakis, Binhang Yuan
arXiv:2606.07124v2 Announce Type: replace-cross
Abstract: We study the minimax estimation error for distributed covariance matrix estimation in the vertical-split (feature-split) setting, where two a...
By Jing Yee Tan, Guangyue Han
Large language model optimization is an active research area, spanning quantization of model weights, early-exit methods for skipping layers, and speculative decoding. Each track uses its own quality...