WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning

https://arxiv.org/abs/2607.28418v1

Core Idea

WIDE introduces the first end-to-end differentiable token-level dynamic width pruning framework for LLMs, enabling fine-grained computation allocation by letting each token select attention-head and FFN-channel groups.

For this daily profile, it is worth opening because it links Attention, Inference, and LLM to a concrete method, not just a broad trend.

What Is New

The novelty signal is concentrated around Attention, Inference, LLM, and Training. For this profile, the important question is whether the paper changes how architecture ideas are generated, evaluated, or connected to software and hardware constraints.

Methodology

Read this as a loop: define the target system, apply the proposed mechanism, measure against a baseline, then use the measured signal to justify the next design choice. Mechanism: Pruning is a promising approach for improving the efficiency of LLMs. Evidence: Recent dynamic sparsity methods improve quality retention by adapting computation to individual inputs, yet they remain largely limited to coarse-grained structural decisions and their practical acceleration under.

score(design) = quality_metric(design) - cost_to_evaluate(design) + feedback_gain(design)

Figure To Read First

Read this visual first: focus on the first architecture, workflow, or pipeline figure before the experiments. It should show what is optimized, what feedback signal is used, and where the system boundary sits.

Minimal Mental Model

research artifact
  question      -> what design, runtime, or system boundary changes?
  mechanism     -> model, agent, compiler, simulator, or hardware feedback
  evaluation    -> baseline comparison plus cost / latency / accuracy signal
  reusable idea -> what should carry into the next architecture experiment?

Why It Matters

Paper recommendations matter when they sharpen the research map: what problem is now easier to study, what methodology becomes reusable, and which architecture assumptions should be questioned next.