Layer Equivalence Is Not a Property of Layers Alone: How You Test Redundancy Changes What You Find
This paper distinguishes two protocols for measuring transformer layer redundancy—replacement (can one layer substitute for another in place?) and interchange (do two layers approximately commute when swapped?)—and shows they can disagree substantially. Experiments on Pythia (410M, 1.4B) and 8B-scale models (Qwen3-8B, Llama-3.1-8B) reveal that the protocol gap grows during training and can change which layers appear safe to prune by several-fold. Notably, Qwen3-8B shows interchange-guided removal is far safer than replacement-guided at the same layer budgets, while Llama-3.1-8B ties the two protocols despite lower interchange KL. The authors recommend scoring both swap-KL metrics before any layer removal or merging, requiring only unlabeled forward passes.
Related guides (2)
Related events (8)
Training-Free Looped Transformers: Inference-Time Recurrence via ODE-Motivated Layer Reapplication
The paper introduces a method to retrofit recurrence onto frozen pretrained transformer checkpoints at inference time by looping a contiguous mid-stack block of layers without any fine-tuning or architectural changes. Naive block reapplication degrades performance, so the authors motivate their approach by treating pre-norm transformer blocks as forward Euler ODE steps and replacing one large update with smaller damped sub-steps. Evaluated across seven model families including dense, sparse MoE, and MLA+MoE architectures, the method yields consistent benchmark improvements (e.g., +2.64 pp on MMLU-Pro for Qwen3-4B-Instruct) at no training cost.
Hyperfitting Explained: Terminal Geometric Expansion in Final Transformer Layers Drives Diversity Gains
This paper investigates the 'hyperfitting' phenomenon—where fine-tuning LLMs to near-zero loss on small datasets improves open-ended generation and reduces repetition—and demonstrates it is mechanistically distinct from temperature scaling. Entropy-matched control experiments falsify both the temperature-equivalence and static vocabulary reweighting hypotheses, instead localizing the effect to a 'Terminal Expansion' in the final transformer block where feature-space dimensionality expands by ~80.8 dimensions, enabling promotion of deep-tail tokens via context-dependent rank reordering. The authors introduce Late-Stage LoRA, a targeted fine-tuning strategy updating only the final 5 layers, achieving robust generation with minimal parameter updates.
Phantom specialization in circuit discovery: structural differences don't imply distinct mechanisms
A new arXiv preprint challenges a core assumption in mechanistic interpretability: that structurally different circuits discovered for the same task imply distinct computational mechanisms. Using Literal Sequence Copying across token-frequency bands in five Pythia models (70M–1.4B), the authors extract 75 circuits and show that structurally distinct circuits implement the same computation, with band-specific edges transferring broadly and a shared core recovering ≥99% of circuit performance. The paper introduces the term 'phantom specialization' for this pattern and argues that standard source-level evaluation inflates apparent faithfulness, while edge-level evaluation and cross-condition transfer tests are needed to detect the many-to-one mapping from structure to function.
Semantic vs. Surface Noise in LLM Agents: 68-Cell Measurement Study with Held-Out Validation
This paper documents an empirical phenomenon across 10 LLMs from 7 architecture families: meaning-bearing perturbations (paraphrase, synonym substitution) cause final-answer inconsistency ~19.69 percentage points more often than presentation-level perturbations (formatting, reordering) of comparable severity, across GSM8K, MATH, and HotpotQA benchmarks. The effect is validated on a held-out 11th model (qwen2.5-14B-Instruct) with 1,800 trajectories. Trace-level analysis supports a 'stealth-divergence' picture where semantic perturbations preserve the first action but induce divergence in intermediate reasoning steps, while two prior mechanism claims are explicitly retracted. The study is notable for its honest reporting of stress-test failures and pre-registered replication.
Causal audit finds routing statistics do not predict expert importance in MoE pruning
A new arXiv paper conducts a token-level interventional audit of Mixture-of-Experts (MoE) pruning heuristics across three architectures (OLMoE-1B-7B, Qwen1.5-MoE, DeepSeek-V2-Lite), finding that no standard observational metric — utilization rates, activation norms, routing weight distributions — reliably predicts which experts can be removed without functional cost. Effect sizes fall below Cohen's d = 0.17 across all 60 metric-layer combinations after multiple-comparison correction, with only a single significant signal at OLMoE's final layer. The authors argue that existing pruning methods succeed not because they identify dispensable experts but because early-layer redundancy makes most selection criteria interchangeable. The work frames this as a concrete counterexample to the broader interpretability practice of treating associational (rung-1) evidence as interventional (rung-2) conclusions.
Expert Tying reduces MoE LLM memory footprint by ~2x with minimal quality loss
Researchers introduce Expert Tying, an architectural modification for Mixture-of-Experts LLMs that shares expert parameters across consecutive transformer layers while keeping routing and attention layer-independent. Evaluated on OLMoE, Qwen3, and DeepSeek-style MoE architectures, the method achieves nearly 2x memory reduction with negligible perplexity or downstream quality degradation. The approach exploits parameter redundancy in MoE pathways to improve the compute-to-memory trade-off for training and inference.
Variable-Width Transformers: X-shaped architecture outperforms uniform-width baselines with 22% fewer FLOPs
Researchers propose the ><former (X-shaped transformer), a decoder-only architecture that uses wider early and late layers with narrower middle layers, implemented via a parameter-free residual resizing mechanism. Evaluated on models from 200M to 2B dense parameters and 3B MoE, the architecture consistently outperforms parameter-matched uniform-width baselines on language modeling loss. The design yields a 22% reduction in FLOPs and 15% reduction in KV cache memory under fitted scaling curves, suggesting nonuniform width allocation is a viable path to more compute-efficient language models.
Survey proposes four-layer architecture for token-operations-oriented LLM inference optimization
A new arXiv preprint introduces a four-layer technical architecture—Multi-model Fusion, Model Optimization, Compute-Model Fusion, and Compute-Network-Model Fusion—for systematically organizing LLM inference optimization techniques. The paper reviews key technologies and industry status at each layer and analyzes their application in real-world business scenarios. The framing around 'token operations' positions inference optimization as an operational discipline analogous to traditional IT operations.