…Tabular Knowledge Distillation through Interaction Diversity of Learned Feature Bins (2026) Please give a thumbs up to this comment if you found it helpful! If you want recommendations for any Paper on…
…GradSentry captures output-altering backdoor signatures using per-sample gradient spectra, avoiding pairwise sample comparisons and clustering during feature construction. Importantly, our method is training-agnostic: it works for both parameter-efficient…
…Discriminative RMs regress rewards directly on features extracted by multimodal large language models (MLLMs) without explicit reasoning, making them prone to shortcut learning and heavily reliant on massive data scaling for generalization…
…We show that both spaces encode linearly separable hallucination-related information, with discriminative power concentrated in a sparse feature subset and increasing toward deeper encoder layers. We propose two steering strategies: activation…
…Given conversational instructions and visual prompts, X2SAM couples an LLM with a Mask Memory module that stores guided vision features for temporally consistent video mask generation. The same formulation supports generic, open…
…Overall, our findings suggest that social role granularity is not merely a stylistic surface feature, but a structured, ordered, and causally manipulable latent direction in role-conditioned language model behavior. View arXiv…
…To preserve gradient unbiasedness despite using trajectory-conditioned features , we introduce a cross-rollout construction that predicts each rollout's value from an independent rollout's internal states. Because POISE estimates prompt…
…Visual Feature Conditioning for Diffusion-Based Super-Resolution (2026) Disentangling Generation and Regression in Stochastic Interpolants for Controllable Image Restoration (2026) Noise-Started One-Step Real-World Super-Resolution via LR-Conditioned…
…A Representation-Pivoted Autoencoder Enhancing Both Image Generation and Editing (2026) Latent-Compressed Variational Autoencoder for Video Diffusion Models (2026) Coevolving Representations in Joint Image-Feature Diffusion (2026) TC-AE: Unlocking Token…
…Feature Space Conditioning for Controllable Image-to-Video Diffusion (2026) Guiding a Diffusion Model by Swapping Its Tokens (2026) Please give a thumbs up to this comment if you found it helpful…