TL;DR for operators A hybrid model can contain relatively little attention and still depend on that attention for its decisive retrieval step. Across 23 measured depth profiles from twelve checkpoints, the intermediate clue needed for a two-hop answer becomes most causally usable immediately before the layer that performs the largest conversion toward the final answer. That conversion occurs in an attention-containing layer in every measured profile. ...
TL;DR for operators If adding an unused token whose hidden state is exactly zero changes existing tokens or predictions, that token is not actually inactive. Standard softmax attention can produce exactly this behavior: a visible zero source still contributes normalization mass even when its value contribution is zero. OAttention1 addresses this at the attention operator by giving each token a norm-derived presence coefficient. The coefficient gates what a receiver emits and, separately, how much support a source contributes to the attention numerator and denominator. Exact zero then means zero participation under the declared operator contract. ...
TL;DR for operators An internal metric can track a capability well enough to be useful for diagnosis and still fail once the training loop is told to maximize it. In this study, an attention-based signal intended to reflect whether demonstrations matter to a model rises from about 0.516 to 1.413 under direct optimization—within 0.5% of its theoretical maximum. Yet the corresponding behavioural effect is essentially absent on the controlled QA probe, and MMLU accuracy falls to 0.279.1 ...
TL;DR for operators A DPO-style preference pair usually contains one prompt and two ranked responses. Conventional execution turns that into two prompt-response sequences, which means the same prompt is processed twice. Jaekyung Cho’s Preference Packing: Efficient Preference Optimization for Large Language Models1 treats that duplication as a systems problem. It stores the prompt once, places the alternative responses behind it, and uses masking plus adjusted position IDs so each response still behaves as though it were paired independently with the prompt. ...
TL;DR for operators A model can receive a camera feed, spoken report, reference image, and text record without meaningfully reasoning across all four. In C$^3$PO1, 86–95% of observed failures across ten models in the paper’s failure analysis were classified as dominance-driven: one modality or prior drove the answer while other evidence was effectively ignored. ...
TL;DR for operators Longer reasoning is not automatically safer for vision-language systems. This paper finds that a model can preserve the relevant visual information yet perform worse once reasoning shifts attention away from the image region that matters. The paper separates two questions that are often conflated in multimodal evaluation: how much attention goes to the image, and whether that attention is concentrated on evidence relevant to the question. Targeted masking experiments suggest that the heads with concentrated visual focus are functionally important, not merely correlated with success. ...
TL;DR for operators Long context becomes expensive for a specific architectural reason: standard self-attention allows every position to interact with every other position. In the usual formulation, that means $O(n^2 d)$ computation and $O(n^2)$ storage for attention-related matrices as sequence length $n$ grows. Hasi Hays’s mathematical monograph on attention1 is useful because it connects that deployment constraint directly to the mechanism that makes attention powerful in the first place. ...
TL;DR for operators An agent has a recurring allocation problem: how much of its past should it bring back before answering a question or choosing its next action? More history increases the chance that useful evidence is available, but it also increases the amount of material competing with the information that matters now. ...
TL;DR for operators Teams are easy to label. Understanding who actually listens to whom is harder. Hong’s paper on learned coordination conventions proposes a diagnostic for inspecting how cooperative reinforcement-learning agents route information between predefined roles.1 The central move is architectural: place role labels in both the querying agent’s representation and each ally’s representation, then use cross-attention to expose a role-to-role routing matrix. ...
Mind the Model: When Generative AI Teaches Neuroscience New Tricks A model is not a mind. This should not need saying, but then again, neither should “do not use benchmark scores as a personality test,” and here we are. The more useful point is subtler. Modern generative AI does not matter to neuroscience because transformers are secretly brains in a hoodie. It matters because machine learning has turned several once-vague ideas about cognition into working engineering mechanisms. Not perfect mechanisms. Not biological mechanisms by default. But mechanisms clear enough to test, stress, reject, adapt, or steal with appropriate academic manners. ...