| 1 | MemFLoRA: Memory-Floor LoRA for CNN Adaptation at the Edge | Mehmet Emre Akbulut, Johannes Geier, Ulf Schlichtmann | cs.LG | 2026-10-06 |
| 2 | Forensic Reserve: Eliciting Latent Knowledge for Image Forgery Detection | Jiahua Li, Zixu John, Tom Zhong +5 | cs.CV | 2026-10-06 |
| 3 | Have I Seen Enough? Frozen Video-Language Models Encode Evidence Readiness | Dan Ben-Ami, Kobi Cohen, Chaim Baskin | cs.CV | 2026-10-06 |
| #4 | Latent space bias directions in LLMs capture confidence, not fairness | Stephanie Buttigieg, Maeve Madigan, Parameswaran Kamalaruban +1 | cs.CL | 2026-10-06 |
| #5 | Test-Time Adaptation of Quantized ViTs via Single-Pass Quantizer-Aligned Recalibration | Hyeongheon Cha, Young D. Kwon, Sung-Ju Lee | cs.CV | 2026-10-06 |
| #6 | Language Unalignability: Why Some Concepts Resist Cross-Cultural Benchmark Evaluation | Shu-Kai Hsieh, Da-Chen Lian | cs.CL | 2026-10-06 |
| #7 | Align, Then Correct: Training-Free Two-Stage Low-Rank Compensation for Extremely Quantized Large Language Models | Seobin Song, Geonho Lee, Janghwan Lee +1 | cs.LG | 2026-10-06 |
| #8 | Do LLMs Act on What They Know? From Partner Representations to Cooperative Actions | Yuhwan Jeong, Jinnyeong Yang, Kuk-Jin Yoon | cs.LG | 2026-10-06 |
| #9 | Feature Encoding in VAE-based Audio Decoders: Effects of Input, Depth and Distribution | Louis McCallum, Mick Grierson | cs.SD | 2026-10-06 |
| #10 | Harness Engineering for Software Engineering via Modular Executable Dev-Primitives | Haibo Jin, Xinjie Li, Peng Kuang +1 | cs.SE | 2026-10-06 |
| #11 | MASKerade: Token-Routed Mask Experts for Dense-to-MoE Upcycling | Mingyuan Zhang, Yue Bai, Zhongruo Wang +5 | cs.LG | 2026-10-06 |
| #12 | TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models | Xin Wang, Hao Yu, Zhengyang Zhuge +9 | cs.LG | 2026-10-06 |
| #13 | The Model Plants the Trigger: Answer-Side Backdoor Attacks in Multi-Turn Large Language Models | Yibo Zhang, Tianrong Guan, Liang Lin +3 | cs.CR | 2026-10-06 |
| #14 | Does Steering Break Your Model? A Multi-Dimensional Evaluation Suite for LLM Steering Methods | Haotian Yang, Huikang Jiang, Yucheng Wu +4 | cs.CL | 2026-10-06 |
| #15 | Neuromotor Hierarchy Network: Physiological Inductive Biases for Robust Generalization in sEMG Decoding | He Wang, Hongyuan Qi, Zhaoxian Zhang +4 | cs.LG | 2026-10-06 |
| #16 | Unlocking Fine-Grained Perception in CLIP via Structurally-Aware Latent Masked Modeling | Juntong Li, Lingwei Dang, Haomin Wu +3 | cs.CV | 2026-10-06 |
| #17 | Massive Activation Gating Channel in Large Language Models | Minjia Mao, Shi Chen, Bowen Yin +1 | cs.AI | 2026-10-06 |
| #18 | Loud and Clear: Dynamic Activation Steering for Improving Speech Intelligibility in Noisy Environments | Seymanur Akti, Alexander Waibel | cs.SD | 2026-10-06 |
| #19 | Activation Denoising: A Robustness View on Parallel vs Sequential LLM Quantization | Yan Scholten, Rachel Lawrence, James Hensman +3 | cs.LG | 2026-10-05 |
| #20 | COMPASS: Finding Where Reasoning Lives in Language Models | Pratyay Dutta, Kowshik Thopalli, Vivek Narayanaswamy | cs.AI | 2026-10-05 |
| #21 | AlignQuant: Tile-Aligned Mixed-Precision Quantization for Efficient LLM Generation | Hanzhi Zhang, Qiao Zhang, Qinglei Cao +4 | cs.LG | 2026-10-05 |
| #22 | Learnable Spectral Activations | Tamir Shor, Or Litany, Alex Bronstein | cs.LG | 2026-10-05 |
| #23 | Defense-in-Depth for LLMs: Evaluating Memory Gates Against Activation-Induced and Memory-Induced Sycophancy | Ritvij Sharma, Russell Dlugosz, Ryan Zhou +1 | cs.AI | 2026-10-05 |
| #24 | Inference and learning in sparse autoencoders as natural gradient flow | Hadi Vafaii, Tejas Rao, David Chanin +6 | cs.LG | 2026-10-05 |
| #25 | Trajectory-Retrieval Speculative Decoding: When Does a Model's Own History Help? | Yuyang Dai, Yushun Dong | cs.AI | 2026-10-05 |
| #26 | Weight Oracles: Reading Neural Network Weights with Language Models | Krishna Kabra, Constantin Venhoff, Christian Schroeder de Witt | cs.LG | 2026-10-05 |
| #27 | Memory-Efficient Expert Routing for Distributed MoE Training | Arnab Kanti Tarafder, Jaume Guasch-Martí, Gokcen Kestor +1 | cs.DC | 2026-10-05 |
| #28 | Distributionally Robust Mixture-of-Experts Training | Xin Teng, Muxiao Li, Hongyi Wen | cs.LG | 2026-10-05 |
| #29 | SoloQ: Calibration-Free Quantization for Diffusion Language Models | Donghyun Lee, Arkapravo Ghosh, Varun Manjunath +5 | cs.LG | 2026-10-05 |
| #30 | BRANCH-MoE: Balance-Aware Tree Routing for Large Embedding Models | Gang Fu, Adel Javanmard, MohammadHossein Bateni +1 | cs.LG | 2026-10-05 |
| #31 | Closing the Context Gap: Activation Alignment for Tabular In-Context Learning | Yoel Zeldes | cs.LG | 2026-10-05 |
| #32 | Separators Make Carry Propagation Learnable:The Geometry of Latent Carry in a Multiplication Transformer | Sama Satariyan, Raphael Cousin, G{é}rard Biau | cs.LG | 2026-10-05 |
| #33 | Will the Judge Flip? Predicting Position-Sensitive LLM Judgments from Residual Stream Activations | Hashmath Shaik, Gnaneswar Villuri, Alex Doboli | cs.LG | 2026-10-05 |
| #34 | Molecules of a Story: Community Detection in PMI-weighted Narrative Networks | Kasper Fyhn, Rebekah Baglini | cs.CL | 2026-10-05 |
| #35 | Before Agent Tells The Lie: Has Deception Already Been Represented? | Xinling Li, Dadi Guo, Qingyu Liu +5 | cs.CL | 2026-10-05 |
| #36 | Proof-Grounded Patient-Specific Clinical Explanations from Knowledge-Graph Reasoning | Surajit Das | cs.AI | 2026-10-05 |
| #37 | FairProp: Fair Node Representation Learning via Differentiable Propagation Layers | Emmanouil Kariotakis, Aritra Konar | cs.LG | 2026-10-05 |
| #38 | Training-Free Transformer Merging via Sequential Local Operator Alignment | Akansh Maurya, Ya-Wei Eileen Lin, Stefanie Jegelka +2 | cs.LG | 2026-10-05 |
| #39 | Steering by Influence: Curvature Aware Data Weighting for Activation Steering | James A. E. Dixon, Stephen J. Roberts, Francesco Quinzan | cs.LG | 2026-10-05 |
| #40 | CentriQ: Calibration-Free Quantization of Diffusion Transformers via Exact Mean Centering | Nataša Jovanović, Mathieu Salzmann, Saqib Javed | cs.CV | 2026-10-05 |
| #41 | RoSA: Rotational Sparse Adaptation for Memory-Efficient Fine-Tuning | Muhammad Azeem Lodhi, Chao Zhou, Rebekka Burkholz | cs.LG | 2026-10-05 |
| #42 | Frequency-Decoupled Diffusion Guidance for Non-Blind Image Deblurring | Sihan Wang, Jinshu Huang, Haibin Su +1 | cs.CV | 2026-10-05 |
| #43 | Cross-lingual Calibration of Pre-Generation Success Probes for Multilingual LLM Routing | Andrea Paganelli, Stefano Civelli, Pietro Bernardelle +1 | cs.CL | 2026-10-05 |
| #44 | Cross-Lingual Transferability of Training Data Extraction Attacks to Recover Memorized PII | Alexandru Nazare, Agnese Profico, Nicolò Vania +6 | cs.CL | 2026-10-05 |
| #45 | Do VLAs Understand and Adapt to the Objects They Handle, or Simply Replay Learned Behaviors? | Xinnuo Xu | cs.RO | 2026-10-05 |
| #46 | TrustMI: Causally controlling how assistants trust their users | Théo Lasnier, Romain Froger, Maxence Lasbordes +1 | cs.CL | 2026-10-05 |
| #47 | Polynomial neural surrogates for designing photonic quantum experiments | Rohit Chaurasiya, Xuemei Gu | quant-ph | 2026-10-05 |
| #48 | Noise Out, Bias In: Targeted Bias Injection in Diffusion Language Models via Closed-Loop Activation Steering | Sarim Hashmi, Mukul Ranjan, Abdelrahman Elsayed +3 | cs.CL | 2026-10-05 |
| #49 | Spatial Supervision Without Attribution Optimization: Improving Post-Hoc Class Activation Maps via Box-Guided Evidence Routing | Wenhao Liang, Liangwei Nathan Zheng, Lin Yue +3 | cs.CV | 2026-10-05 |
| #50 | fMRI-TAMCL: Text-Anchored Supervised Multimodal Contrastive Learning for fMRI-Based Brain Disorder Classification | Juliana Mantebea Danso, Enoch Opanin Gyamfi, Mylene C. Q. Farias | cs.CV | 2026-10-05 |