20 results for “attention”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
The paper introduces the Attention Redistribution Attack (ARA), a white-box adversarial method that bypasses safety alignments in LLMs by manipulating the attention mechanism's geometry, showing that…
The paper proposes SISA (SSM-Informed Softmax Attention), a novel hybrid attention mechanism that integrates state-space model (SSM) importance signals directly into the attention score, achieving sta…
This paper presents a novel attention mechanism, fixed-query oscillator attention, that replaces softmax attention on energy-constrained physical substrates.
The paper proposes DOA, a training-free attention policy that leverages self-attention in decoder-only SpeechLLMs to achieve high-quality, low-latency simultaneous long-form translation without requir…
This paper introduces Spectral Attention and Graph Convolutional Attention (GCA) for denoising graphs, which outperforms linear attention and provably utilizes the input graph spectrum.
Yan Wang, Xiulong Yuan, Kaiming Yang, Jiaxuan Peng +15 more
Libra is a load balancing approach for long-context LLM training that groups packed sequences into fixed-size pools and reduces attention workload variance, improving end-to-end throughput and straggl…
Moment-KV introduces a novel momentum-based technique to compress the Key-Value (KV) cache during the decoding phase of LLM generation, significantly improving fidelity in long-generation tasks.
This paper proposes a model-intrinsic XAI framework for transformer-based ASR models to improve faithfulness and temporal grounding of explanations.
The paper proposes a method to approximate the behavior of attention heads in transformer language models with executable programs.
The paper introduces Agent-Radar, a training-free method that dynamically steers multi-agent attention toward relevant context using a novel decay mechanism, significantly improving performance in lon…
This paper introduces instruction-based vector steering to redistribute attention in Large Audio-Language Models (LALMs) and demonstrates its effectiveness in recovering sound event locations.
Timing Yang, Predrag Neskovic, Jansen Seheult, Wenchao Han +3 more
This paper proposes a self-supervised visual model called RATS that discovers compositional structure in images.
This paper provides a theoretical understanding of attention mechanisms in identifying relevant information from large collections of tokens.
HodgePhaseNet introduces a new representation for semantic transitions as an antisymmetric real-valued 1-cochain on a finite oriented simplicial complex.
This paper introduces GazeLNN, a computationally lightweight scanpath prediction model for robot autonomy.
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…