arXiv:2605.08563v1 Announce Type: new Abstract: When an LLM agent fails a multi-step tool-augmented task and retries, the failed attempt typically remains in its context window — contaminating the next attempt and elevating the per-step error rate beyond the base level.…
When it comes to emissions, individual driving patterns matter as much as how “green” the regional electricity mix is, MIT researchers report.
arXiv:2602.17251v3 Announce Type: replace Abstract: Electroencephalography (EEG) foundation models (EFMs) have shown strong potential for transferable representation learning, yet their adaptation in realistic settings remains challenging when only a few labeled subjects are available. We show that this challenge stems…
arXiv:2605.00445v3 Announce Type: replace Abstract: Large Language Models have achieved remarkable success and are increasingly deployed in critical applications involving tabular data, such as Table Question Answering. However, their robustness to the structure of this input remains a critical, unaddressed…
arXiv:2506.09110v4 Announce Type: replace Abstract: Electroencephalography (EEG) provides real-time insights into brain activity and supports diverse applications in neuroscience. While EEG foundation models (EFMs) have emerged to address the scalability issues of task-specific models, current approaches still yield clinically uninterpretable…
arXiv:2512.13751v2 Announce Type: replace Abstract: Expanding pre-trained language models offers a practical way to increase capacity without training larger models from scratch. Depth Up-Scaling (DUS) does so by duplicating Transformer blocks and inserting them into a pre-trained backbone. This process…
arXiv:2605.09654v1 Announce Type: cross Abstract: Sampling from score-based diffusion models incurs bias due to both time discretisation and the approximation of the score function. A common strategy for reducing this bias is to apply corrector steps based on the unadjusted…
arXiv:2605.10566v1 Announce Type: cross Abstract: Probabilistic linear solvers (PLSs) return probability distributions that quantify uncertainty due to limited computation in the solution of linear systems. The literature has traditionally distinguished between Bayesian PLSs, which condition a prior on information obtained…
arXiv:2605.08114v1 Announce Type: new Abstract: We analyse three KV cache quantization schemes under a fair bit budget: textbf{KV} (scalar MSE baseline), textbf{KQV} (WHT + MSE on $K$; WHT + MSE + QJL on $V$), and textbf{QKQV} (WHT + MSE +…
arXiv:2605.08896v1 Announce Type: cross Abstract: Robust adaptation of LLMs and VLMs is often evaluated by average accuracy or average consistency under perturbations. However, these averages can hide a structured failure mode: a prediction may remain correct while probability mass already…
