| 2026-11-12 | 2611.12869 | Where Does Alignment Emerge and What Does It Mean? A Closer Look at the Platonic Representation Hypothesis | Julia Herbst et al. | arXiv | 6 | |
| 2026-11-04 | 2610.40574 | Every Token Needs Its Own Teacher: Multi-teacher Adaptive On-policy Self-distillation | Yifu Luo et al. | arXiv | 13 | |
| 2026-11-03 | 2610.32878 | Advancing SVD-based LLM Compression via Layer-Wise Error Model Search | Moritz Thoma et al. | arXiv | 4 | |
| 2026-10-22 | 2610.26397 | Bridged Self-Distillation for On-Policy Learning | Runsheng Chen et al. | arXiv | 4 | |
| 2026-10-21 | 2610.27190 | On the Fragility of Tasks under Composition: Implicit Budgeting in Language Models | Chenpan Li et al. | arXiv | 11 | |
| 2026-09-28 | 2608.09444 | Depth-adaptive Inference of Looped Language Models via Continuous Depth Batching | Kristian Schwethelm et al. | arXiv | 9 | |
| 2026-09-01 | 2608.29847 | ContextBias: Controlled Evaluation of Bias Persistence Under Context Shift in Text-to-Image Models | Shaghayegh Kolli et al. | arXiv | 5 | |
| 2026-08-27 | 2608.15062 | Gated Recurrent Transformers: Expressive Depth through Recurrent Modulation | Amr Hegazy et al. | arXiv | 11 | |
| 2026-06-22 | 2606.20527 | StylisticBias: A Few Human Visual Cues Drive Most Social Biases in MLLMs | Shaghayegh Kolli et al. | arXiv | 4 | |
| 2026-06-04 | 2605.31559 | Functional Attention: From Pairwise Affinities to Functional Correspondences | Jiefang Xiao et al. | arXiv | 2 | |
| 2026-06-03 | 2606.03287 | BA-T: An Iterative Transformer for Two-View Bundle Adjustment | Ganlin Zhang et al. | arXiv | 1 | |
| 2026-05-14 | 2605.13542 | RealICU: Do LLM Agents Understand Long-Context ICU Data? A Benchmark Beyond Behavior Imitation | Chengzhi Shen et al. | arXiv | 6 | |
| 2026-05-14 | 2605.10315 | Active Tabular Augmentation via Policy-Guided Diffusion Inpainting | Zheyu Zhang et al. | arXiv | | |
| 2026-05-04 | 2605.00414 | Trees to Flows and Back: Unifying Decision Trees and Diffusion Models | Sai Niranjan Ramachandran et al. | arXiv | 7 | |