arXiv:2602. 06127v2 Announce Type: replace Abstract: The high computational demands of Large Language Models (LLMs) motivate methods that reduce parameter count and accelerate inference.
arXiv:2504.04342v2 Announce Type: replace Abstract: Scaling up model parameters and training data consistently improves the performance of large language models (LLMs), but at the cost of rapidly gro...
The paper revisits the impact of pruning on large language models (LLMs) during test-time scaling (TTS). While prior work found that structured pruning degrades reasoning performance, this study shows that unstructured pruning—removing only specific redundant weights—can actually improve TTS performance on reasoning benchmarks for models s1.1-7B and Qwen3-8B, sometimes surpassing the full-weight models. The authors also examine how different layer-wise sparsity allocation strategies affect these outcomes.
arXiv:2608. 06901v1 Announce Type: cross Abstract: Vision-language models (VLMs) have achieved remarkable generalization across diverse multimodal tasks through large-scale pre-training, yet their rapidly increasing computational and memory requirements pose significant challenges for deployment in constrained environments.
arXiv:2608. 12953v1 Announce Type: cross Abstract: Structured pruning is a promising approach for compressing large language models (LLMs), yet existing methods rely heavily on greedy heuristics that produce myopic decisions, and often fail to precisely meet target compression budgets.
SHIFT-LLM is a training‑free post‑pruning correction framework that inserts a Linear Residual Adapter (LRA) at each depth‑pruned site in large language models. Each LRA preserves the original residual identity while adding a lightweight affine correction calibrated via closed‑form least‑squares regression on a small held‑out set, thereby approximating the hidden state that would have been produced by the removed block. Experiments across multiple model families and benchmarks show that SHIFT‑LLM consistently recovers accuracy lost to depth pruning, achieving gains up to +15.7 points on Llama‑3.1‑8B‑Instruct with only a few hundred calibration samples and no gradient computation.
arXiv:2509. 14230v2 Announce Type: replace Abstract: While structured pruning presents a highly effective pathway for accelerating Large Language Model (LLM) inference, existing methods frequently suffer from significant performance degradation and demand computationally retraining to recover capabilities.
MWOP (Modality-aware Width-wise Operation Pruning) is a method that independently prunes visual‑to‑visual, text‑to‑visual, and text‑to‑text attention paths within each layer of multimodal large language models, and separately selects feed‑forward network channels for visual and textual inputs. It uses a first‑order Taylor criterion to guide pruning, re‑evaluates FFN importance after attention pruning, and applies LoRA‑based recovery training. The approach is paired with path‑sparse Triton attention kernels and compact visual‑side FFN execution to achieve practical acceleration, preserving token sequences while reducing computation. "whyItMatters":"MWOP achieves a 1.6× prefill speedup on LLaVA‑OneVision‑7B while retaining 99.7% performance, and further boosts token‑compression methods to 2.9× and 2.7× speedups, demonstrating its effectiveness across architectures."
arXiv:2602. 02599v4 Announce Type: replace Abstract: Long-context inference in large language models (LLMs) is bottlenecked by the memory and compute of the key-value (KV) cache.
arXiv:2609.06557v1 Announce Type: new Abstract: Large language models (LLMs) are often considered fragile under aggressive sparsification, and maintaining reliable performance typically requires stic...
arXiv:2609.24485v1 Announce Type: new Abstract: Visual token pruning is a promising approach to reducing the inference cost of large vision-language models (LVLMs), yet aggressive token reduction oft...
arXiv:2605. 18331v2 Announce Type: replace Abstract: Large Language Models (LLMs) have experienced significant growth and development in recent years.
arXiv:2606. 09080v1 Announce Type: new Abstract: Pruning has emerged as a dominant paradigm for accelerating large language model (LLM) inference, spanning a broad spectrum of methods that remove computation across tokens, layers, heads, dimensions, and attention patterns.