A deep network's loss is invariant to continuous symmetries of its parameters: the logit shift, the ReLU rescaling, the LayerNorm scale, the per-head attention rotation. Adam's per-coordinate preconditioner drifts along each symmetry orbit, which pulls the trajectory off the symmetry quotient where the optimization lives and blurs the singular-learning rate the quotient makes readable.
arXiv:2606. 29176v1 Announce Type: new Abstract: A deep network's loss is invariant to continuous symmetries of its parameters: the logit shift, the ReLU rescaling, the LayerNorm scale, the per-head attention rotation.
By Tejas Pradeep Shirodkar
arXiv:2606. 12629v3 Announce Type: replace-cross Abstract: The standard basis of transformer hidden states is a training-free, architecture-general feature basis for detecting concepts and, in language models, steering them; with no learned dictionary.
By Varun Reddy Nalagatla
arXiv:2607. 16821v1 Announce Type: cross Abstract: Task arithmetic, sequential fine-tuning, activation steering, and first-order random search all operate through relatively small perturbations around an already trained checkpoint, and they rely on different local approximations: individual perturbations should be first-order predictable, task updates should compose with controlled interference, useful tangent structure should be stable and possible to estimate, and weight edits should have counterparts in representation space.
By Irina Piontkovskaia, Sergey Nikolenko
arXiv:2606. 19491v1 Announce Type: new Abstract: Pretrained transformers sit near singular minima of the loss, where the Fisher information metric degenerates along dead directions: directions in parameter space along which the directional Fisher vanishes.
By Tejas Pradeep Shirodkar, P. J. Narayanan
arXiv:2606. 07559v1 Announce Type: cross Abstract: Fine-tuning a language model on contexts whose correct completion has a near-synonym competitor often fails silently.
By Vaibhav Prakash, Jayasri Dontabhaktuni
arXiv:2606. 12629v1 Announce Type: cross Abstract: We show that the standard basis of transformer hidden states already provides a training-free, architecture-general feature basis.
By Varun Reddy Nalagatla
arXiv:2605. 28149v2 Announce Type: replace Abstract: Sparse Autoencoders (SAEs) extract interpretable features from Large Language Model activations, but standard variants enforce non-negative latents, so a bidirectional semantic axis (e.
By Bartosz Wieciech, Zmnako Awrahman, Marcin Czelej, Victor Hugo Jaramillo Velasquez, Wioletta Stobieniecka
arXiv:2607. 04926v1 Announce Type: cross Abstract: How does the way information reaches a transformer -- as symbolic tokens, a clean per-factor "oracle" code, or an entangled perceptual vector -- shape whether it binds that information compositionally?
By Yoshiyuki Ootani
arXiv:2606. 26538v1 Announce Type: cross Abstract: Deep Transformers are composed of uniformly stacked residual blocks, yet their deepest layers often add little value.
By Huzama Ahmad, Cao Viet Hai Nam, Se-Young Yun
arXiv:2608. 05136v1 Announce Type: new Abstract: Gradient descent on a factored model $W = UV^\top$ is implicitly biased toward low-rank solutions, while Adam, starting from the same small initialization, is not.
By Devender Singh
arXiv:2607. 12501v3 Announce Type: replace Abstract: The Forward-Forward algorithm trains each layer locally, so that a scalar goodness - the sum of squared activations - is high on real inputs and low on contrastive ones.
By Paolo Giannitrapani