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 proposes using an auxiliary reconstruction task, specifically one that captures intra-state feature dependencies, to improve the quality of state representations learned by the encoder in ne…

The paper proposes a novel geometric embedding hashing method to recover object correspondences (vector links) between two embedding clouds generated by different black-box encoders using only a small…

Clark Hash is a stateless, deterministic quantization method that significantly reduces the storage size of neural embeddings while maintaining high accuracy for cosine similarity search.

LoSATok proposes a low-dimensional semantic-acoustic tokenizer that efficiently compresses high-dimensional audio features into a compact latent space, significantly improving the performance and effi…

The paper proposes explicitly disentangling positional and semantic representations in Transformer encoders, demonstrating that this separation allows for a clearer understanding of how positional inf…

Echo is a joint-embedding predictive architecture that uses a single, pretrained ViT encoder to simultaneously perform speaker diarization, speech recognition, and dynamic source separation in a share…

The paper proposes a unified framework for designing efficient and expressive token mixing layers by separating the direct and recurrent influences of inputs, allowing for a principled trade-off betwe…

The paper proposes PrefixMem, a dedicated encoder for Semantic IDs (SIDs), demonstrating that structured, prefix-conditioned representations significantly improve the accuracy and recall of generative…

The paper introduces Morlet Positional Encoding (MoPE), a novel wavelet-based positional encoding that models position and locality simultaneously, outperforming standard sinusoidal and RoPE methods.

This paper introduces BBOmix, an open-source benchmark for unsupervised representation learning on real-world biological data.

The paper proposes and evaluates a novel embedding model for bidirectional function association between source code and decompiled/stripped code, significantly outperforming existing models.

The paper proposes Locality-Aware Redundancy Pruning (LoRP), a training-free method that prunes LLM layers by exploiting localized inter-layer redundancy, leading to improved efficiency while maintain…

AdaCodec introduces a predictive visual coding scheme for video MLLMs, significantly improving efficiency and performance by transmitting only inter-frame changes and full reference frames when necess…

The paper demonstrates that positional encodings are not necessary for transformers to achieve universal computation, showing that the inherent mechanism of sliding context windows already provides su…

The paper introduces Residualized Sparse Autoencoders (ReSAEs) to improve multi-layer interventions in transformers by training each layer on the residual activation, which better preserves cross-laye…