This paper investigates the use of contrastive objectives for brain decoding using functional MRI (fMRI) activity and shows that linear contrastive decoders outperform other methods.

The paper introduces SB-ECC, a novel score-based decoder that models error correction as continuous-time denoising, achieving state-of-the-art performance across various code families and noise levels…

A new boosting algorithm that strong learns concept classes closed under O(log 1/γ)-XOR using O(log 1/ε) calls to a γ-advantage weak learner and additional samples, by connecting boosting with list-de…

This paper proves that the maximum of up to 10 real numbers can be exactly represented by a ReLU network with two hidden layers, and shows that the same depth bound holds for all continuous piecewise-…

This paper proves that the min-plus factorization rank and tropical rank of a binary linear code's conditional decoding matrix equal 2^s, where s is the classical state complexity of the minimal trell…

The paper introduces Hybrid Verified Decoding, a method that predicts the acceptance length of a cache draft to intelligently select between cache verification and model-based drafting, achieving sign…

This paper develops a theory for speculative decoding in practical language model inference systems, where success is governed by local ranking and threshold events.

This paper isolates the effect of state update design in causal self-attention and introduces structural interventions to reduce approximation errors, outperforming prior post hoc baselines on long-co…

This paper theoretically justifies the strong performance of linear recurrent neural networks as memory units in partially observable reinforcement learning by constructing specific linear filters tha…

This paper proves that for any finite abelian group, there exists a spectral sparsifier for its Cayley graph with log(|G|) generators. This result improves upon previous work for constructing code spa…

This paper develops a new decoding algorithm for Desarguesian spread codes to uniquely decode in the presence of insertions and deletions, even when the sum of their dimensions exceeds half the minimu…

The paper introduces CFGzip, an offline token space compression technique that significantly reduces the computational overhead of constrained decoding, making complex grammar enforcement feasible at…

This paper proves that random linear codes have nearly optimal discrepancy properties in various regimes, extending classical results and enabling new applications.

This paper improves the lower bound on the maximum size of trifferent codes using a locally sparse hypergraph and the Verstraete-Wilson theorem.

The paper establishes information-theoretic lower bounds for stochastic optimization using low-bit gradients by reducing the problem to compressed Gaussian mean estimation, yielding sharp bounds on co…

The paper introduces HOLA (Hippocampal Linear Attention), a semiparametric test-time memory system that combines a compressive linear-attention state with a bounded exact cache for key-value associati…