Papersby GlyphWinning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning research paper by Alibaba (Qwen), 2025
Alibaba (Qwen) · Inference and efficiency · Sep 28, 2025 · 11 citations · 61 upvotes · unverified
What it shows
Quadrant-based Tuning (Q-Tuning) optimizes both sample and token pruning in supervised fine-tuning of large language models, achieving superior performance with reduced data.
By Shaobo Wang, Jiaming Wang, Jiajun Zhang and 8 more · arXiv 2509.23873 · PDF · Code
UnverifiedHugging Face's summary; not yet checked by hand.
More from Alibaba (Qwen)
All 78Co-Design Bench: Multimodal Collaborative Coding Evaluation for Agentic ModelsCo-Design Bench evaluates how effectively coding agents update software applications based on user requests with text, images, and other media.
Alibaba (Qwen)23 upvotesRead →Qwen-Image-PE: Learning Visual Design for Text-to-Image Prompt EnhancementQwen-Image-PE improves text-to-image prompts via two-stage training with caption-based reverse distillation and groupwise design rewards, scaling across data, model size, and information density.Alibaba (Qwen)23 upvotesRead →World-in-Context: Interactive Video World Modeling with In-Context ConditioningWorld-in-Context unifies view, action, and camera controls via explicit tokens and interaction-aware positional encoding to improve interactive video generation and navigation.Alibaba (Qwen)22 upvotesRead →Beyond Watching and Searching: Benchmarking Agents for Video-centered Deep Research ReportsThis benchmark evaluates how well AI agents can research and synthesize information from videos to produce interactive reports.Alibaba (Qwen)19 upvotesRead →UserArena: Benchmarking Interactive User Simulation for Long-Horizon Shopping AgentsUserArena introduces a real-world interactive benchmark with long-horizon shopping trajectories and an evaluation framework, alongside On-Policy Trajectory Distillation to improve simulator fidelity for agentic recommendations.Alibaba (Qwen)55 upvotesRead →SWIFT: Self-guided Weak-to-strong dIFfusion models via Target extrapolationThis training method uses a smaller, frozen model to guide the training of a larger diffusion model, improving quality without increasing inference costs.Alibaba (Qwen)30 upvotesRead →BlenderWorld: Benchmarking Visual Agents for 3D Creation from Real-World ReferencesThis benchmark evaluates how well AI models can perform complex 3D creation and editing tasks within the Blender software.Alibaba (Qwen)23 upvotesRead →CommerceGen-Studio: An End-to-End Framework for Commercial-Grade Main-Image GenerationThis paper presents an end-to-end framework for generating commercial-grade e-commerce product images by combining metadata extraction, layout planning, and multi-condition generation.Alibaba (Qwen)25 upvotesRead →
Other inference and efficiency papers
TopicEfficient Memory Management for Large Language Model Serving with PagedAttentionvLLM manages the KV cache like pages of virtual memory, serving models with 2 to 4 times the throughput.
UC Berkeley9,965 citations72 upvotesRead →FlashAttention: Fast and Memory-Efficient Exact Attention with IO-AwarenessFlashAttention computes exact attention with far fewer GPU memory reads and writes, making long sequences faster.
Stanford University5,830 citations16 upvotesRead →Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse AttentionNSA, a trainable sparse attention mechanism, enhances long-context modeling efficiency without sacrificing performance, achieving improvements in speed and accuracy over full attention models.
DeepSeek596 citations157 upvotesRead →SmolVLM: Redefining small and efficient multimodal modelsSmolVLM, a series of compact multimodal models, achieves high performance with minimal GPU memory usage, making efficient deployment on mobile and edge devices possible.
Hugging Face330 citations212 upvotesRead →Chronos-2: From Univariate to Universal ForecastingChronos-2, a pretrained model with a group attention mechanism, achieves state-of-the-art performance in zero-shot univariate, multivariate, and covariate-informed forecasting tasks.
Amazon276 citations28 upvotesRead →Inference-Time Scaling for Generalist Reward ModelingSelf-Principled Critique Tuning enhances pointwise generative reward modeling for large language models, improving scalability and quality compared to existing methods.DeepSeek259 citations59 upvotesRead →
Amazon276 citations28 upvotesRead →Inference-Time Scaling for Generalist Reward ModelingSelf-Principled Critique Tuning enhances pointwise generative reward modeling for large language models, improving scalability and quality compared to existing methods.About this paper
- Venue
- arXiv.org
- Citations
- 11, 0 influential · Semantic Scholar
- Upvotes
- 61 · Hugging Face
- Lab
- Alibaba (Qwen) · on Companies · on Quarterly
Changes
Citations rose from 9 to 11.
A first count of 0 influential citations.
A first count of 9 citations.
Found by the weekly Hugging Face scan; not yet checked by hand.