pruna — Pruna is a model optimization framework built for developers, enabling you to deliver faster, more efficient models with minimal overhead.
デベロッパー向けのモデロプティミゼーションフレームワークです。モデルの高速化と効率化を実現することができます。
モデロプティミゼーション
MLINFO COLLECTION
Bayesian Optimization
少数試行で条件探索を進めるベイズ最適化、実験計画、ブラックボックス最適化を扱います。
記事一覧
1 / 18DeepSpeed — DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
分散トレーニングと推論を容易、効率的に実行するためのディープラーニング最適化ライブラリです。
ディープラーニング最適化ライブラリ
Work Agents: Systems, Capabilities, and Optimization
As foundation models evolve from information generation to digital work execution, agents are increasingly capable of completing complex tasks across tools, applications, and workflows. However,…
generative-ai
Multiscale Policy Optimization for Long-Horizon LLM Agents
Long-horizon LLM agents interact with their environments through complete assistant turns while generating each action token by token. We observe that critic values vary primarily across turns,…
nlp
RSIHub: A Composable Framework for Agent-Evolution Methods
Agent-evolution methods use execution feedback to improve prompts, skills, tools, and orchestration, but their implementations often rebuild the same experimental machinery. We present RSIHub, an…
nlp
Skill^{infty}: Recursive Self-Improvement for Agent Skill Optimization
Recursive self-improvement (RSI), in which a system also improves the way it improves, is a long-standing aspiration on the path to AGI. Language agents increasingly store procedural knowledge in…
computer-vision
Multi-Token Prediction Done Right
Multi-Token Prediction (MTP) is now a common ingredient in language-model pre-training, as it improves downstream performance and enables faster inference through speculative decoding. We identify a…
deep-learning
Principia: Test-Time Hypotheses to Principle Construction for Scientific Discovery
Scientific discovery requires identifying the scientific principles underlying observed phenomena to guide further investigation. As these empirical principles are often unknown in complex discovery…
nlp
The fixed-point bundle method over product-of-simplex domains arising from game equilibria
Developing general-purpose algorithms with global asymptotic convergence guarantees for Nash equilibria of general-sum games remains a longstanding challenge. This paper extends the fixed-point…
math-theory
Learning from Fleet Experience: A Collective Learning Paradigm for Robots
Experience generated during deployment offers an opportunity for robots to improve policy reliability through learning from their own executions. However, learning through human corrections requires…
nlp
A Broader Look into MLLM's Retrieval Heads
Locating relevant evidence in long inputs is a core capability of Multimodal Large Language Models. Prior studies attribute this capability to retrieval heads, a sparse set of attention heads that…
nlp
HiP3R: Hierarchical Pose Graphs for Long-Horizon 3D Reconstruction
Feed-forward models accurately estimate camera motion and 3D geometry from short video windows. However, computational and memory costs prevent direct inference on sequences containing thousands of…
deep-learning
A path-following framework on fiber bundle for variational inequalities
Developing general-purpose algorithms with global asymptotic convergence guarantees for variational inequalities (VIs) remains a longstanding challenge. This paper proposes a path-following framework…
math-theory
PhysSkin++: Real-Time and Generalizable Physics-Based Animation via Self-Supervised Neural Skinning
Generalizing real-time physics-based animation across diverse 3D shapes and spatial discretizations remains challenging. In this paper, we introduce PhysSkin++, a physics-informed framework that…
deep-learning
CoworkEnv: Synthesizing Training Environments for Long-Horizon Cowork Agents
AI coworkers must coordinate tools, communicate across turns, and act on changing workspace state while respecting workflow constraints. Constructing training experience for these capabilities…
nlp
HoloBoxing: A Simple Recipe for Humanoid Boxing with 7 Minutes of Single-GPU Training
HoloBoxing presents a simple recipe for learning humanoid boxing by building on a pretrained whole-body controller. The recipe separates reusable motor skills from task decisions: a compact planner…
nlp
Steering Black-Box Large Language Model Agents with Pitfall Anticipation World Model
Frontier black-box Large Language Model (LLM) agents are proficient at long-horizon reasoning and precise action generation. However, when it comes to a specific agentic task, they have no…
nlp
HarnessPro: Recursive Harness Self-Improvement with Pareto Optimization for Performance-Cost Trade-offs
Harness development plays a crucial role in building capable AI agents. Recent approaches improve harnesses through recursive self-improvement (RSI), but their performance gains often come with…
nlp
Function-Space Temporal Self-Distillation for Policy Optimization
Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in language models, but scalar outcomes provide coarse supervision over response trajectories. Self-distillation offers denser…
deep-learning
Answering in the User's Variety: Calibrated Accommodation Pairs for Post-Training
People adapt how they talk to the person in front of them. However, chat models tend to respond in Standard English regardless of the dialect used by the user.
nlp
OR-License: Evaluating LLM Agents as Real-World Operations Research Practitioners
Can large language model (LLM) agents deliver expert-level operations research (OR) solutions directly from original client materials, without prior expert reformulation? Existing OR benchmarks…
nlp
Self-Evolving Coding Agents via Harness-Policy Optimization
Large language model (LLM) agents have shown promising potential in coding tasks, and their performance is jointly determined by the policy model and the harness that mediates their interaction with…
nlp
MolLean: A Process-Verifiable Language for Chemical Reasoning
Chemical chain-of-thought can contain hallucinated structural and property claims. We thereby introduce MolLean, a process-verifiable language that grounds chemical reasoning in an explicit molecular…
nlp
EdgeKernelBench: Unified LLM-Driven Kernel Generation for Edge Backends
Recent works show that LLMs can generate kernels with strong performance on server GPUs. Edge deployment presents distinct challenges because the hardware is heterogeneous, the software stacks are…
nlp