arXiv:2607. 04428v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) generate text by iteratively denoising a masked sequence, offering a parallel alternative to autoregressive models, but eliciting strong reasoning through post-training remains difficult: supervised fine-tuning is off-policy and suffers from exposure bias, while reinforcement learning gives only sparse, sequence-level rewards and is hard to apply without tractable sequence likelihoods.
By Phuong Tuan Dat, Qi Li, Xinchao Wang
arXiv:2607. 04558v1 Announce Type: cross Abstract: Automated detection of interictal epileptiform discharges in scalp electroencephalography (EEG) is clinically important, but recent high-performing deep-learning models often trade interpretability for accuracy.
By Sonali Santhosh, Kelly Shuhong Yu, Eugene Chang, Jonathan Kim, Kie Shidara, Danilo Bernardo
arXiv:2607. 04698v1 Announce Type: new Abstract: The rapid proliferation of Internet of things (IoT) devices has significantly expanded the cyber-attack surface, necessitating robust and privacy-preserving intrusion detection systems (IDS).
By Mohammad Ansarimehr, Somayeh Changiz, Ehsan Baghishani, Ali Mousavi
arXiv:2605. 17758v2 Announce Type: replace Abstract: Synthetic data is widely used in healthcare to create datasets that preserve statistical properties of real data without exposing sensitive patient information.
By Nitish Nagesh, Pengbao Zhou, Atchuth Naveen Chilaparasetti, Yajat Nagaraj Kiran, Tu Nguyen, Arshia Harish Puthran, Muhjaazee Love, Aadi Sharma, Mahdi Bagheri, Ian Harris, Amir M. Rahmani
arXiv:2605. 24042v3 Announce Type: replace-cross Abstract: Of $1{,}536$ Gaussian release covariances we tested for single-layer hidden-state privacy, zero achieve both moderate utility and moderate privacy against an adaptive retrieval attacker.
By Alexander Okezue Bell
arXiv:2604. 02923v4 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have demonstrated advanced capabilities but often suffer from factual inaccuracies (hallucinations) and systematic biases.
By Shuai Wu, Xue Li, Yanna Feng, Yufang Li, Zhijun Wang, Ran Wang
arXiv:2607. 03585v1 Announce Type: new Abstract: Engineering Digital Twins and Prognostics and Health Management (PHM) systems rely on robust perception modules to extract actionable information from heterogeneous and non-stationary time-series data.
By Quang Hung Pham, Ryad Zemouri, Martin Gagnon, Luc Vouligny
arXiv:2503. 06269v3 Announce Type: replace-cross Abstract: Traditional white-box methods for creating adversarial perturbations against LLMs typically rely only on gradient computation from the targeted model, ignoring the internal mechanisms responsible for attack success or failure.
By Thomas Winninger, Boussad Addad, Katarzyna Kapusta
arXiv:2607. 04777v1 Announce Type: new Abstract: Graph-structured data is increasingly generated and stored in decentralized environments, such as social platforms, mobile applications, and edge networks, where users maintain control over their local graph data.
By Longzhu He, Peng Tang, Chaozhuo Li, Jinhu Fu, Litian Zhang, Li Sun, Philip S. Yu, Sen Su
arXiv:2508. 21010v3 Announce Type: replace-cross Abstract: Existing Causal-Why Video Question Answering (VideoQA) models often struggle with higher-order reasoning, relying on opaque, monolithic pipelines that entangle video understanding, causal inference, and answer generation.
By Paritosh Parmar, Eric Peh, Basura Fernando
arXiv:2603. 22770v2 Announce Type: replace-cross Abstract: The deployment of deep neural networks (DNNs) in safety-critical edge environments necessitates robustness against hardware-induced bit-flip errors.
By Alan T. L. Bacellar, Sathvik Chemudupati, Shashank Nag, Allison Seigler, Priscila M. V. Lima, Felipe M. G. Fran\c{c}a, Lizy K. John
arXiv:2506. 23845v2 Announce Type: replace-cross Abstract: While sparse autoencoders (SAEs) have generated significant excitement, a series of negative results have added to skepticism about their usefulness.
By Kenny Peng, Rajiv Movva, Jon Kleinberg, Emma Pierson, Nikhil Garg
arXiv:2607. 04306v1 Announce Type: new Abstract: Distilling a fine-tuned teacher into a LoRA-adapted student is a standard recipe for parameter-efficient compression, but output-level KD does not explicitly control which rank-$r$ weight subspace the adapter occupies.
By Omer Tariq, Syed Muhammad Raza, Jeongbae Son
arXiv:2504. 08791v3 Announce Type: replace-cross Abstract: On-device inference offers privacy, offline use, and instant response, but consumer hardware restricts large language models (LLMs) to low throughput and capability.
By Zonghang Li, Tao Li, Wenjiao Feng, Rongxing Xiao, Jianshu She, Hong Huang, Mohsen Guizani, Hongfang Yu, Qirong Ho, Wei Xiang, Xue Liu
arXiv:2604. 16926v2 Announce Type: replace-cross Abstract: Electroencephalography (EEG) foundation models have shown strong potential for learning generalizable representations from large-scale neural data, yet their clinical deployment is hindered by distribution shifts across clinical settings, devices, and populations.
By Gabriel Jason Lee, Jathurshan Pradeepkumar, Jimeng Sun
arXiv:2602. 18037v2 Announce Type: replace-cross Abstract: Reinforcement Learning from Human Feedback (RLHF) or Verifiable Rewards (RLVR) are two key steps in the post-training of modern Language Models (LMs).
By Johannes Ackermann, Michael Noukhovitch, Takashi Ishida, Masashi Sugiyama
arXiv:2607. 03125v1 Announce Type: new Abstract: Deep reinforcement learning (DRL) offers powerful control for industrial cyber-physical systems (ICPSs), but its "black-box" exploration risks violating strict hardware safety limits.
By Georg Sch\"afer, Jakob Rehrl, Stefan Huber
arXiv:2607. 03517v1 Announce Type: new Abstract: Brownian Bridge Diffusion Models (BBDM) offer an appealing framework for image restoration and inverse problems by constructing a stochastic bridge from the clean signal directly to the degraded observation, rather than to pure noise.
By Ron Levi, Michael Elad
arXiv:2504. 09662v4 Announce Type: replace-cross Abstract: Multi-agent large language model simulations have the potential to model complex human behaviors and interactions.
By Jenny Ma, Riya Sahni, Karthik Sreedhar, Lydia B. Chilton
arXiv:2508. 04796v3 Announce Type: replace-cross Abstract: Tokenization is the first -- and often least scrutinized -- step of most NLP pipelines.
By Negar Foroutan, Clara Meister, Debjit Paul, Joel Niklaus, Sina Ahmadi, Antoine Bosselut, Rico Sennrich