inference speedup

6 papers

• BoltzNCE: Learning likelihoods for Boltzmann Generation with Stochastic Interpolants and Noise Contrastive Estimation
• Compress Large Language Models via Collaboration Between Learning and Matrix Approximation
• Curriculum Design for Trajectory-Constrained Agent: Compressing Chain-of-Thought Tokens in LLMs
• GAMMA: Gated Multi-hop Message Passing for Homophily-Agnostic Node Representation in GNNs
• StruDiCO: Structured Denoising Diffusion with Gradient-free Inference-stage Boosting for Memory and Time Efficient Combinatorial Optimization
• VITA-Audio: Fast Interleaved Audio-Text Token Generation for Efficient Large Speech-Language Model