This paper proposes Supervised Memory Training (SMT), a method for training nonlinear RNNs that sidesteps recurrent credit propagation entirely.

This paper proposes a novel non-autoregressive (NAR) decoding framework based on minimum Bayes' risk (MBR) for speech recognition, which outperforms previous NAR decoding and runs faster than autoregr…

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…

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 proposes SimSD, a plug-and-play speculative decoding algorithm that adapts diffusion language models (dLLMs) to achieve fast, token-level acceleration by restoring causal masking capabilitie…

The paper proposes Speculative Pipeline Decoding (SPD), a novel framework that uses pipeline parallelism to accelerate LLM inference by processing multiple tokens in parallel, achieving higher speedup…

Physical AI inference (batch-1 decode) is primarily memory-bandwidth-bound, but the observed latency gap between fast and slow GPUs is not solely due to memory bandwidth, as launch-side overheads beco…

The paper applies network science to demonstrate the feasibility of unsupervised dependency parsing in non-human primates due to their sequence length distribution.

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.

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…

The paper analyzes order-agnostic language models (OALMs), finding that their learned conditionals are not true factorizations and proposing a variance-based diagnostic to compare the quality of diffe…

PrunePath introduces a budget-adaptive structured sparsification framework that efficiently prunes Feed-forward networks in large language models, achieving hardware-friendly sparsity and measurable s…

The paper proposes SpeechKV, a method to compress speech sequences inside large language models using a learned pooling, maintaining performance and delivering decoding speedup.

DominoTree, a new best-first draft tree method for LLM inference, achieves up to 6.6x speedup over autoregressive decoding and the highest mean accept length, using a GPU-native CUDA-graph builder.

Chatterbox-Flash introduces a prior-calibrated block diffusion model for zero-shot TTS that achieves high-fidelity, streaming synthesis with significantly lower computational overhead than existing me…

The paper theoretically analyzes the properties that optimal sparse autoencoder (SAE) dictionaries must satisfy, deriving constraints that explain observed SAE behaviors like hierarchical splitting an…

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…