SVD-Surgeon: Training-free optimal singular value compensation for LLM compression
SVD-Surgeon applies the Optimal Brain Surgeon (OBS) framework to singular-value decomposition-based LLM compression, computing closed-form updates to retained singular values that compensate for pruned ones to second order in the model loss. The method is training-free and modular, designed to layer on top of existing SVD compressors. Applied to SVD-LLM on OPT and LLaMA 2-7B, it improves the perplexity-compression trade-off without retraining.
Related guides (2)
Related events (8)
SubFit: Submodule-Level Fitted Residual Replacement for LLM Compression
SubFit introduces a post-training LLM compression method that operates at the submodule level (Attention and FeedForward separately) rather than full layers, and selects components non-contiguously. The approach replaces removed submodules with lightweight fitted residual bypasses calibrated on small data. Evaluated across ten LLMs at sparsity levels from 12.5% to 37.5%, SubFit retains 84.6% of dense downstream accuracy at 25% sparsity versus 81.6% for the strongest baseline, while reducing perplexity degradation from 4.34x to 2.42x and delivering measurable inference speedup and KV-cache savings.
LLMSurgeon: Post-Hoc Auditing of LLM Pretraining Data Mixtures
LLMSurgeon formalizes Data Mixture Surgery (DMS), a framework for estimating the domain-level distribution of an LLM's pretraining corpus using only generated text from the target model. The method casts DMS as an inverse problem under the label-shift assumption, using a calibrated soft confusion matrix to correct domain confusion and recover the latent mixture prior. The authors also introduce LLMScan, a verifiable evaluation suite built from open-source LLMs with known pretraining mixtures, on which LLMSurgeon demonstrates high-fidelity recovery of domain compositions without access to training data.
Variance-Calibrated Modulation (VCM): training-free decoding intervention to address LLM likelihood trap
Researchers propose Variance-Calibrated Modulation (VCM), a training-free pre-decoding method that reshapes LLM probability distributions before truncation to combat repetitive degeneration and vocabulary dullness. VCM combines two mechanisms: Contextual Searchlight via PMI (suppressing stopwords, elevating context-relevant tokens) and Adaptive Self-Debiasing (scale-invariant penalization using real-time logit standard deviation). Evaluated across open-ended generation, factual QA, and mathematical reasoning, VCM improves diversity, coherence, and reasoning accuracy at higher temperatures with negligible overhead. The method is compatible with existing decoding strategies like Top-p and Min-p.
Ω-QVLA: Training-Free W4A4 Quantization for Full Vision-Language-Action Models Including Diffusion Action Heads
Omega-QVLA is a post-training quantization framework that compresses both the LLM backbone and the diffusion-based action head of VLA models to uniform W4A4 precision without mixed-precision schemes or fine-tuning. It combines composite SVD-Hadamard rotation for weight energy equalization with per-step DiT activation scaling to handle dynamic-range drift across denoising steps. On the LIBERO benchmark, it achieves 98.0% and 87.8% task success on Pi 0.5 and GR00T N1.5 respectively—matching or exceeding FP16 baselines—while reducing static memory footprint by 71.3%. Real-world manipulation experiments confirm the approach generalizes beyond simulation.
Demystifying Data Organization for Enhanced LLM Training
This Microsoft Research paper systematically investigates how data organization—distinct from data selection—affects LLM training efficiency across pre-training and SFT stages. The authors formalize four guidelines (Boundary Sharpening, Cyclic Scheduling, Curriculum Continuity, and Local Diversity) and introduce two novel data ordering methods, STR and SAW, that reuse pre-computed sample-level scores with minimal additional overhead. Experiments across multiple model scales and dataset sizes demonstrate improved training stability and performance, with code released publicly.
Vision-OPD: On-Policy Self-Distillation for Fine-Grained Visual Understanding in MLLMs
Vision-OPD addresses a 'regional-to-global perception gap' in multimodal LLMs, where models answer fine-grained visual questions more accurately when given cropped evidence regions than full images. The method instantiates a crop-conditioned teacher and full-image-conditioned student from the same MLLM, minimizing token-level divergence along on-policy rollouts to transfer regional perception to the full-image policy. This self-distillation requires no external teacher models, ground-truth labels, reward verifiers, or inference-time tools. Benchmarks show competitive or superior performance against larger open-source, closed-source, and agentic 'Thinking-with-Images' models.
PC Layer: Polynomial weight preconditioning for stable LLM pre-training
Researchers propose a PC (preconditioning) layer that applies polynomial preconditioning to reshape the singular-value spectrum of weight matrices during LLM training, improving conditioning stability. The preconditioned weights merge back into the original architecture at inference time with no overhead. Experiments on Llama-1B pre-training show advantages over standard transformers for both AdamW and Muon optimizers, with theoretical convergence guarantees for deep linear networks.
Latent Context Language Models (LCLMs) achieve competitive encoder-decoder KV cache compression at scale
Researchers introduce Latent Context Language Models (LCLMs), a family of encoder-decoder compressors that map long token sequences to shorter latent embeddings consumed by a decoder, targeting the KV cache memory bottleneck in long-context inference. The authors conduct architecture search and continually pre-train 0.6B-encoder/4B-decoder models on over 350B tokens at compression ratios of 1:4, 1:8, and 1:16. LCLMs improve the Pareto frontier across general-task performance, compression speed, and peak memory, and are demonstrated as efficient backbones for long-horizon agents that can skim compressed context and expand relevant segments on demand. The work closes a previously noted gap between encoder-decoder approaches and KV cache compression methods on the accuracy-efficiency frontier.