arXiv:2607. 04118v1 Announce Type: cross Abstract: With the rise of parametric memory, LoRA-based External Parametric Memory (EPM) has emerged as a modular solution, but existing routing methods often introduce additional training, deployment, and maintenance overhead.
arXiv:2606. 06467v1 Announce Type: cross Abstract: Long-context inference in modern LLMs is increasingly constrained by decoding efficiency, especially in reasoning-heavy settings where models generate long intermediate chains of thought.
arXiv:2607. 07953v1 Announce Type: cross Abstract: Self-attention lets each token retrieve information from the full context, but its quadratic cost in sequence length limits training and inference at long context.
arXiv:2603. 24787v2 Announce Type: replace Abstract: Routing has emerged as a promising strategy for balancing performance and cost in large language model (LLM) systems that combine lightweight models with powerful but expensive large models.
arXiv:2606. 12412v1 Announce Type: cross Abstract: Vision-language models (VLMs) project images into hundreds to thousands of visual tokens, making decoder inference expensive in both attention computation and KV-cache memory.
arXiv:2606. 09514v1 Announce Type: new Abstract: Large language models (LLMs) incur high inference cost due to their depth and parameter scale.
arXiv:2608. 11519v1 Announce Type: new Abstract: Full self-attention is a strong token mixer for PDE surrogates on irregular domains, but its quadratic cost limits its use on high-resolution problems.
arXiv:2608. 05303v1 Announce Type: cross Abstract: On-device deployment of Large Language Models (LLMs) has become essential for personalized edge applications.
arXiv:2608. 05872v1 Announce Type: cross Abstract: Standard Large Language Models (LLMs) execute layers sequentially.
arXiv:2606. 00144v1 Announce Type: cross Abstract: Speculative decoding speeds up autoregressive decoding by using a drafter to propose multiple tokens that a verifier validates in parallel.
arXiv:2606. 12243v1 Announce Type: cross Abstract: Speculative decoding (SD) addresses the high inference costs of LLMs by having lightweight drafters generate candidates for large verifiers to validate in parallel.
arXiv:2602. 17993v2 Announce Type: replace-cross Abstract: Complex problems, whether in math, logic, or planning, are solved by humans through a sequence of steps where the result of one step informs the next.
arXiv:2606. 01838v1 Announce Type: cross Abstract: Agentic language model systems alternate between two structurally distinct step types: structured tool calls (short, deterministic, low perplexity) and open-ended planning/reasoning steps (long, complex, high perplexity).