No Free Swap: Protocol-Dependent Layer Redundancy in Transformers
arXiv:2605.16234v2 Announce Type: replace-cross Abstract: When researchers ask whether two transformer layers are “equivalent” for compression, they often conflate distinct…
Training data attribution in diffusion models via mirrored unlearning and noise-consistent skew
arXiv:2605.17938v1 Announce Type: cross Abstract: Training data attribution (TDA) should enable generative model interpretability and foster a variety of related…
BacktestBench: Benchmarking Large Language Models for Automated Quantitative Strategy Backtesting
arXiv:2605.17937v1 Announce Type: cross Abstract: Quantitative backtesting is essential for evaluating trading strategies but remains hampered by high technical barriers…
Bridging Silicon and the Hippocampus: Algebro-Deterministic Memory “VaCoAl” as a Substrate for Vector-HaSH and TEM
arXiv:2605.15652v2 Announce Type: replace-cross Abstract: Vector-HaSH and the Tolman-Eichenbaum Machine propose the hippocampal-entorhinal circuit factorizes content from a grid-cell scaffold,…
DeepSlide: From Artifacts to Presentation Delivery
arXiv:2605.15202v1 Announce Type: new Abstract: Presentations are a primary medium for scholarly communication, yet most AI slide generators optimize the…
CLOVER: Closed-Loop Value Estimation and Ranking for End-to-End Autonomous Driving Planning
arXiv:2605.15120v2 Announce Type: replace-cross Abstract: End-to-end autonomous driving planners are commonly trained by imitating a single logged trajectory, yet evaluated…
Looped SSMs: Depth-Recurrence and Input Reshaping for Time Series Classification
arXiv:2605.16048v1 Announce Type: cross Abstract: State Space Models (SSMs) are inherently recurrent along the sequence dimension, yet depth-recurrence – reusing…
XSearch: Explainable Code Search via Concept-to-Code Alignment
arXiv:2605.16046v1 Announce Type: cross Abstract: Semantic code search has been widely adopted in both academia and industry. These approaches embed…
TFGN: Task-Free, Replay-Free Continual Pre-Training Without Catastrophic Forgetting at LLM Scale
arXiv:2605.15053v2 Announce Type: replace-cross Abstract: Continually pre-training a large language model on heterogeneous text domains, without replay or task labels,…