TOPIC · EFFICIENCY · 69 PAPERS

Efficient training & inference

LLMs Reasoning Alignment Agents Multimodal Visual generation Vision & 3D Robotics & embodied AI Efficient training & inference Safety & interpretability AI for Science Code & SWE Benchmarks & data Reinforcement learning

Last 30 days 69

#05 ▲371 ★115 ❝2 2026-10-13

Jeva: System One Models from First Principles

Jeva is a decision-native System 1 model that scores candidate options directly instead of generating text answers, making it fast and cacheable.

National University of Singapore · Qi Li, Xinchao Wang

LLMs Efficient training & inference arXiv Code HF

#08 ▲375 ★210 ❝1 2026-10-13

VideoJev: System One Model for Video Understanding and Interaction

VideoJev scores time spans and answer options directly, unifying temporal grounding and video QA for fast decisions.

Multimedia Computing Group-Nanjing University · Yuhan Zhu, Xiangyu Zeng, Qingyi Si +15

Multimodal Efficient training & inference arXiv Code HF

#12 ▲113 ★2.8k ❝1 2026-10-07

Long-WAM: Scaling the Context of World-Action Models

Long-WAM scales the context of world-action models under real-time limits and finds autoregressive video pretraining makes long history pay off.

NVIDIA · Wei Huang, Bohan Zhang, Chenzhi Liu +13

Robotics & embodied AI Efficient training & inference arXiv Code HF

#22 ▲511 ★7 ❝2 2026-09-29

The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation

Extrapolates RL-induced hidden-representation residuals in on-policy distillation so students can surpass teachers more stably.

Affiliation unverified · Hao Li, MeiJia Chen, Weijie Ren +4

Efficient training & inference Reinforcement learning arXiv Code HF

#26 ▲727 ★5 ❝0 2026-10-15

PremiseCheck: Efficient Fact-Checking of Human and AI Peer Reviews

ReviewFact labels factual errors in peer reviews; PremiseCheck combines an LLM with cheap decision models to verify them efficiently.

Affiliation unverified · Dingjie Song, Zhiling Yan, Ziqian Zhang +2

Benchmarks & data Efficient training & inference arXiv Code HF

#27 ▲560 ★17 ❝0 2026-10-15

MJev-Spatial: System One Spatial Intelligence via Native Attention Matching

MJev-Spatial casts spatial questions as classification over candidates, answering relation, distance and point queries faster than text generation.

Mind Lab · Luozheng Qin, Yuhan Zhu, Changhai Zhou +9

Multimodal Efficient training & inference arXiv Code HF

#30 ▲602 ★7 ❝0 2026-10-14

LEV: Thinking Fast and Deep with Looped Decision Models

LEV lets decision models think deeper by looping their layers instead of generating reasoning tokens.

Affiliation unverified · Dingjie Song, Zhiling Yan, Yuxuan Zhang +1

Reasoning Efficient training & inference arXiv Code HF

#41 ▲167 ★303 ❝0 2026-10-08

REMORY: Learning Residual Memory for Context Compaction

REMORY appends learned soft memory tokens after a summary so long-horizon agents lose less when compacting context.

Fusion Lab: Generative Vision Lab of Fudan University and SII · Hanchen Xia, Baoyou Chen, Yutang Ge +5

Agents Efficient training & inference arXiv Code HF

#47 ▲181 ★57 ❝1 2026-09-28

Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation

Normalises each teacher's feedback strength by domain in multi-teacher on-policy distillation so one student learns maths, code and instruction following.

Nanyang Technological University · Xin Li, Hao Jiang, Xin Gao +6

Efficient training & inference Reinforcement learning arXiv Code HF

#51 ▲143 ★63 ❝0 2026-10-08

TokenRouter: Efficient Serving System for Token-Level LLM Routing

TokenRouter is a serving system for token-level LLM routing that fixes step desynchronisation and batching delays.

Tsinghua-NICS-EFC · Tianyu Fu, Tengxuan Liu, Ruoxi Wang +4

Efficient training & inference arXiv Code HF

#57 ▲101 ★56 ❝1 2026-10-02

DuoMatching: Joint-Marginal Distribution Matching for Few-Step Video Generation

DuoMatching matches both joint and per-frame marginal distributions to improve quality and alignment in few-step video generation.

ByteDance · Jiahao Zhan, Yan Wang, Yongrui Ma +5

Visual generation Efficient training & inference arXiv Code HF

#58 ▲94 ★78 ❝4 2026-09-30

GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed

GroundAnything decodes grounding outputs in parallel with bidirectional diffusion, keeping precision while being much faster.

XPENG AI · Qize Yu, Lianrui Fan, Bowen Ping +19

Vision & 3D Efficient training & inference arXiv Code HF

#60 ▲119 ★272 ❝0 2026-10-19

MemT-1.0: Towards Memory-Native Evolution

MemT-1.0 makes memory intrinsic to the model using Gated DeltaNet-2 and Mixture-of-Storage to scale native memory.

MemTensor · Zhiyu Li, Zeyu Zhang, Linyun Liu +71

LLMs Efficient training & inference arXiv Code HF

#70 ▲218 ★10 ❝0 2026-10-15

Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation

Waypoint-OPD uses an intermediate teacher checkpoint to transfer only consistent RL-induced policy shifts to the student.

Affiliation unverified · Bingxi Hou, Guochao Jiang, Guofeng Quan +4

Reinforcement learning Efficient training & inference arXiv Code HF

#73 ▲131 ★101 ❝0 2026-09-29

STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization

STEPQuant studies where and when quantisation errors matter in linear-attention recurrent states, enabling low-precision state storage.

Zhejiang University · Bingchen Yao, Haobo Xu, Haokun Lin +6

Efficient training & inference arXiv Code HF

#75 ▲38 ★115 ❝6 2026-09-21

Harness-Zero: Harness Distillation via Agent-as-Harness

Harness-Zero distils the gains of specialised agent harnesses into model weights so they persist under a single fixed harness.

Peking University · Haoran Ye, Yuxing Lu, Haonan Dong +2

Agents Efficient training & inference arXiv Code HF

#77 ▲205 ❝1 2026-09-28

On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics

A controlled study isolating on- vs off-policy rollouts in distillation, finding a more nuanced picture than 'on-policy is always better'.

University of Cambridge · Julianna Piskorz, Antonin Berthon, Mihaela van der Schaar

Efficient training & inference Reasoning arXiv HF

#81 ▲75 ★763 ❝0 2026-09-26

MassAlloc Attention: Let Attention Allocate Its Own Compute

MALA attention allocates post-score computation by normalised contribution, skipping negligible work to save compute.

Beijing Academy of Artificial Intelligence · Jingze Shi, Zhangyang Peng, Xianduo Li +6

Efficient training & inference arXiv Code HF

#82 ▲30 ★224 ❝19 2026-09-21

Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents

Jev-Mem uses a fast System 1 control plane to manage agent memory, removing costly generation from the critical path.

Affiliation unverified · Dongming Jiang, Yi Li, Bingzhe Li

Agents Efficient training & inference arXiv Code HF

#84 ▲62 ★102 ❝1 2026-09-28

Improving Test-Time Scaling with Adaptive Looped Transformers

Studies looped transformers under test-time scaling and proposes adaptive looping to beat baselines at matched compute.

Tsinghua-NICS-EFC · Yichen You, Tianyu Fu, Aosong Feng +4

Reasoning Efficient training & inference arXiv Code HF

#90 ▲327 ❝0 2026-09-26

Scaling Properties of Same-Family On-Policy Distillation

Studies scaling of same-family on-policy distillation, finding accuracy rises roughly linearly with KL distance early in training.

Zhejiang University · Yuntai Bao, Qinfeng Li, Guoqing Jiang +5

Efficient training & inference Reinforcement learning arXiv HF

#92 ▲67 ★763 ❝0 2026-09-26

CoWindow Attention: Full Causal Coverage Is a Collective Property

CoWA attention splits long-range history across KV heads so each is sparse yet together they cover the full causal context.

Beijing Academy of Artificial Intelligence · Jingze Shi, Zhangyang Peng, Xianduo Li +6

Efficient training & inference arXiv Code HF

#102 ▲70 ★91 ❝0 2026-10-06

VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs

VisionWeave lets MLLMs learn end-to-end where and how finely to spend visual tokens, adapting to image content.

Qwen · Yuan Feng, Qize Yang, Ruizhe Chen +9

Multimodal Efficient training & inference arXiv Code HF

#104 ▲80 ★49 ❝0 2026-10-03

ALoDLM: Adaptively Looped Diffusion Language Models

ALoDLM adds token-adaptive latent recurrence to diffusion language models, narrowing the quality gap with autoregressive models.

Amazon · Liancheng Fang, Zhuowei Li, Youngeun Kim +10

LLMs Efficient training & inference arXiv Code HF

#105 ▲44 ❝40 2026-09-22

JEV-as-a-Judge: Accept When Confident, Escalate When Unsure

Uses a decision-only judge as a cheap first pass and escalates to stronger judges only when unsure.

Carnegie Mellon University · Yubo Li, Yidi Miao, Ramayya Krishnan +1

Benchmarks & data Efficient training & inference arXiv HF

#106 ▲124 ★30 ❝0 2026-09-30

FrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation

FrameMorrow selects history frames by future relevance via prospective tokens for efficient, consistent long video generation.

National University of Singapore · Bo Yin, Xiaobin Hu, Jiaqi Zhao +1

Visual generation Efficient training & inference arXiv Code HF

#109 ▲30 ★2.1k ❝0 2026-10-06

NeMo-DCR: Bit-Exact Delta-Compressed Refit for Scalable Agentic RL at Trillion-Parameter Scale

NeMo-DCR syncs only the ~1% of weights that change per step, bit-exactly, to speed trillion-parameter agentic RL refits.

NVIDIA · Songlin Jiang, Zhiyu Li, Terry Kong +5

Efficient training & inference Reinforcement learning arXiv Code HF

#115 ▲52 ★51 ❝5 2026-10-01

Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success Rate but 65% Fewer Tokens

Has robot agents compose primitives into locally retried Python cells, raising success while cutting token use.

DAGroup-PKU · Ruiyang Si, Jianxin Bi, Shunyu Yang +12

Robotics & embodied AI Agents Efficient training & inference arXiv Code HF

#119 ▲120 ❝1 2026-09-30

Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents

Mid-Harness samples and verifies candidate actions before execution, improving terminal-agent reliability.

NVIDIA · Minki Kang, Ryo Hachiuma, Shaokun Zhang +8

Agents Efficient training & inference arXiv HF

#120 ▲251 ❝0 2026-10-09

Beyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation

Adds cross-teacher guarding to multi-teacher on-policy distillation to reduce gradient conflicts between domain teachers.

jingdong · Shi-Yu Tian, Yong Liu, Ximan Liu +10

Efficient training & inference arXiv HF

#129 ▲237 ❝0 2026-10-19

Scaling Parameter-Efficient Fine-Tuning for Brain Encoding

Uses parameter-efficient fine-tuning to adapt multimodal backbones of up to 104B for brain encoding, better predicting neural responses.

Mind Lab · Zhuofan Josh Ying, Guanglong Sun, Nolan Ho +6

AI for Science Efficient training & inference arXiv HF

#131 ▲76 ★34 ❝1 2026-10-04

SearchJev: A Fast and Calibrated System-1 Model for Search Agents

SearchJev is a fast, calibrated System 1 model that makes relevance and action decisions for search agents.

Affiliation unverified · Congfeng Cao, Lipeng Zuo, Konstantinos Papakostas +6

Agents Efficient training & inference arXiv Code HF

#135 ▲47 ★215 ❝1 2026-10-20

SolarRenderer: Few-Step Generative Reference Rendering

SolarRenderer adds two LoRAs to a frozen video model to render coarse structural video into realistic footage in four steps, including real-time streaming.

Show Lab · Guian Fang, Shengju Qian, Dongyue Lu +6

Visual generation Efficient training & inference arXiv Code HF

#139 ▲152 ❝0 2026-10-05

LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches

LoGRA cuts RL post-training memory with low-rank gradient sketches and keeps training stable with predicted-KL step control.

NVIDIA · Shaokun Zhang, Yifan Zhang, Jian Hu +5

Reinforcement learning Efficient training & inference arXiv HF

#147 ▲92 ★28 ❝0 2026-09-22

Disaggregated Quantization: Specializing LLM Prefill and Decode

Disaggregated quantisation specialises formats and weights for prefill and decode separately to balance speed and accuracy.

IST Austria Distributed Algorithms and Systems Lab · Andrei Panferov, Maximilian Kleinegger, Sweta Priyadarshi +2

Efficient training & inference arXiv Code HF

#153 ▲90 ★26 ❝0 2026-10-07

GRACE: Generation-aware latent compression for efficient video generation

GRACE further compresses the video latent while staying compatible with the pretrained DiT, speeding up video generation.

KAIST AI · Jiyoung Kim, Paul Hyunbin Cho, Jisu Nam +5

Visual generation Efficient training & inference arXiv Code HF

#154 ▲64 ★20 ❝0 2026-10-14

ActionOPD: Distilling Decisions, Not Tokens

ActionOPD distils agents at the level of semantic actions rather than tokens to transfer decisions to smaller models.

Tsinghua-NICS-EFC · Huining Yuan, Xiangmin Yi, Zelai Xu +5

Agents Efficient training & inference arXiv Code HF

#159 ▲93 ★21 ❝0 2026-10-15

Speculative Forcing for Efficient Autoregressive Video Generation

Speculative Forcing treats intermediate estimates as drafts and accepts converged tokens early to speed up autoregressive video generation.

NAVER AI Lab · Hyunwook Choi, Seungryong Kim, Dongyoon Han +1

Visual generation Efficient training & inference arXiv Code HF

#163 ▲93 ★29 ❝0 2026-09-29

SAKI: Maximal-Coupling-Routed Teacher Supervision for On-Policy Distillation

SAKI routes distillation supervision using KL-constrained teacher-guided rollouts and maximal coupling to help weak students.

meituan · Miteto Wei, Xiaohan Wang, Zehao Chen +7

Efficient training & inference arXiv Code HF

#165 ▲98 ❝1 2026-10-01

World Action Modeling with Progressive Visual Planning

ProWAM predicts actions plus an ordered sequence of sparse visual subgoals, guiding long-horizon control more efficiently than full video.

Meta · Fei Zhang, Zhaochong An, Duncan Frost +5

Robotics & embodied AI Efficient training & inference arXiv HF

#166 ▲21 ★619 ❝1 2026-10-04

Prism: Dynamic Sparse Attention for Native 2K Joint Video-Audio Generation Model Training

Prism is dynamic sparse attention that focuses on sound-producing regions for training native 2K joint video-audio models.

Tencent Hunyuan · Shuyuan Tu, Qi Tian, Yinming Huang +8

Visual generation Efficient training & inference arXiv Code HF

#169 ▲118 ★5 ❝0 2026-10-13

Pack Light, CarryOn: Building Object-Oriented Context for Long-Horizon Agents

CarryOn organises long-horizon agent context around reusable task objects instead of reprocessing history.

McAuley-Lab · Yuchen Lu, Julian McAuley, Lei Zhang

Agents Efficient training & inference arXiv Code HF

#173 ▲57 ★19 ❝0 2026-09-16

RayOrch: Programming and Executing Lineage-Controlled Multi-Grain Dataflows for Foundation-Model Data Preparation

RayOrch is a distributed dataflow engine for foundation-model data prep that preserves lineage while batching efficiently.

Peking University · Xiaochen Ma, Zimo Meng, Junzhu Liang +13

Efficient training & inference arXiv Code HF

#179 ▲46 ★46 ❝0 2026-10-05

MC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion Transformers

MC-Sparse is training-free sparse attention that selects individual KV tokens with cached compensation, closing the dense-sparse gap in DiTs.

Tencent Hunyuan · Jiarui Chen, Zeqiang Lai, Jiangshan Wang +5

Visual generation Efficient training & inference arXiv Code HF

#182 ▲103 ★7 ❝0 2026-09-26

Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs

HeteroFold transfers KV caches across different model families, avoiding repeated prefill in heterogeneous multi-agent systems.

University of Southern California · Vincent-Daniel Yun, Woosang Lim, Haneul Yoo +3

Efficient training & inference Agents arXiv Code HF

#184 ▲81 ★30 ❝0 2026-09-26

DoSA: Dots Sparse Attention

DoSA uses bounds to reject keys early, speeding up sparse attention without changing exact Top-K selection.

dots studio · Fanxu Meng, Taosong Fang

Efficient training & inference arXiv Code HF

#189 ▲23 ★2.9k ❝0 2026-10-05

RealtimeWAM: One-Step Asynchronous World Action Models

RealtimeWAM generates actions in one step with asynchronous inference to make world-action models real-time.

Nanyang Technological University · Chengtao Lv, Jinyang Du, Shuyi Feng +7

Robotics & embodied AI Efficient training & inference arXiv Code HF

#191 ▲56 ★12 ❝2 2026-09-21

All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts

A script-aware mixture-of-experts gives one multilingual scene-text recogniser that is simpler than per-language models and lighter than VLMs.

Fudan University · Xingsong Ye, Yongkun Du, Jiaxin Zhang +6

Vision & 3D Efficient training & inference arXiv Code HF

#196 ▲108 ❝0 2026-09-28

Periodic Weak Spots: Phase Sensitivity from Chunked KV-Cache Compression

Finds chunked KV-cache compression causes phase sensitivity: retrieval accuracy varies with position relative to window boundaries.

ByteDance Seed · Xingyu Zhu, Pu, Yi +6

Efficient training & inference arXiv HF

#197 ▲82 ★13 ❝0 2026-10-14

LatentLoop: Scaling Looped MoE Models with Asymmetric Compute Allocation

LatentLoop finds loop visits in looped MoE play asymmetric roles and allocates compute asymmetrically for better results.

Affiliation unverified · Zefeng He, Yunkai Chai, Xiaoyang Chen +5

Efficient training & inference arXiv Code HF

#199 ▲84 ★10 ❝0 2026-10-14

Speculative Sampling in Interactive Video Generation

Speculative Sampling for interactive video generation caches predictions from large windows to get large-chunk quality at small-chunk latency.

university of science and technology of china · Yubo Huang, Yuxuan Zhang, Jiaming Liu +2

Visual generation Efficient training & inference arXiv Code HF

#201 ▲35 ★49 ❝3 2026-10-05

Towards Looped Models Done Right, Part II: Rethinking at Fixed Points

Driving looped language models towards fixed points enables truncated backprop, KV sharing and cheaper RL with little accuracy loss.

Institute of Foundation Models · Benhao Huang, Chufan Shi, Junlin Chen +4

Efficient training & inference LLMs arXiv Code HF

#217 ▲58 ★38 ❝0 2026-10-12

AReA: Adaptive Receptive-Field Attention for Efficient High-Resolution Diffusion Transformers

AReA adapts the attention receptive field across denoising steps so diffusion transformers generate beyond-training resolutions more cheaply.

University of Toronto Computer Science · Javad Rajabi, Koorosh Roohi, David B. Lindell +1

Visual generation Efficient training & inference arXiv Code HF

#220 ▲91 ★4 ❝0 2026-10-14

Recovering Reliable Supervision via Critique-Guided On-Policy Distillation

CriticOPD has the teacher critique wrong student rollouts before rewriting, restoring reliable supervision in on-policy distillation.

Affiliation unverified · Kaixiang Zhao, Tianrun Yu, Shangzhe Li +4

Efficient training & inference Reasoning arXiv Code HF

#229 ▲80 ★2 ❝1 2026-09-26

X-Tree: Tokenizing Reusable Experience for Efficient Agent Generalization

X-Tree tokenises recurring sub-procedures in agent trajectories and trains on that hierarchy, improving generalisation without LLM calls.

University of Waterloo · Sitao Cheng, Xunjian Yin, Zhiyuan Sun +4

Agents Efficient training & inference arXiv Code HF

#230 ▲50 ★37 ❝0 2026-10-09

Multi-Stream Attention Residuals

Multi-Stream Attention Residuals extend depth-wise attention residuals to multiple heads, with sizeable gains at little extra cost.

Shanghai Jiao Tong University · Xiaohan Qin, Xiangdong Zhang, Tuo Dai +7

LLMs Efficient training & inference arXiv Code HF

#231 ▲41 ★123 ❝0 2026-10-13

FlashVSR+: Efficient Video Super-Resolution via Hybrid Attention and Reward-Yield Distribution Matching

FlashVSR+ speeds up one-step video super-resolution with hybrid attention and aligns it to human preference via reward-weighted distribution matching.

MMLab-CUHK · Ruchang Yao, Shi Guo, Junhao Zhuang +7

Visual generation Efficient training & inference arXiv Code HF

#232 ▲25 ★826 ❝0 2026-10-15

Intern-Decision: Efficient Multimodal Decision Making with Autoregressive Masked Language Modeling

Intern-Decision (0.8B–4B) returns structured choices with probabilities instead of free text, making agent decisions faster.

Intern Large Models · Tong Zhu, Zhe Xu, Zefeng He +7

Multimodal Agents Efficient training & inference arXiv Code HF

#235 ▲91 ❝0 2026-10-06

TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models

Qwen's TRACE aligns the training and rollout FP4 quantisation paths for low-precision RL of MoE language models.

Qwen · Xin Wang, Hao Yu, Zhengyang Zhuge +9

Efficient training & inference Reinforcement learning LLMs arXiv HF

#242 ▲80 ★6 2026-10-19

SpecMRL: Redesign Matryoshka Representation Learning within Parametric Spectrum

SpecMRL reorganises features on a parameter-derived spectral basis so Matryoshka prefixes carry the most important information.

Affiliation unverified · Zhongxin Chen, Songhao Wu, Heng Cui +3

Efficient training & inference arXiv Code HF

#255 ▲68 ★10 ❝0 2026-09-29

E-MoE: Enhanced Mixture-of-Experts for Non-Factorized Diffusion Language Models

E-MoE improves non-factorised diffusion language models with enhanced mixture-of-experts, raising few-step quality without posterior collapse.

Affiliation unverified · Arseny Ivanov, Alexander Kolesov, Alexander Korotin +2

LLMs Efficient training & inference arXiv Code HF

#257 ▲65 ★12 ❝0 2026-09-28

PDE-JEPA: Predictive Representation Learning of Latent Dynamics Modeling for Parametric PDEs

PDE-JEPA learns latent dynamics of parametric PDEs with predictive (JEPA-style) pretraining instead of reconstruction.

Zhejiang University · Zhentao Tan, Jianrong Zhang, Ruijie Quan +1

AI for Science Efficient training & inference arXiv Code HF

#269 ▲73 ❝0 2026-10-14

Cortex: Consolidating Context into Parametric Memory

Cortex consolidates gains from context into parametric memory, keeping them after the context is removed.

ByteDance Seed · Jintian Zhang, Feng He, Xinnian Liang +5

LLMs Efficient training & inference arXiv HF

#272 ▲38 ★10 ❝0 2026-10-01

Selection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents

SSR has small models select from predefined reasoning candidates instead of free generation, cutting cost for multimodal search agents.

Carnegie Mellon University · Feiyu Gavin Zhu, Xiaoyu Zhu, Jiqi Yang +9

Reasoning Efficient training & inference Agents arXiv Code HF

#273 ▲60 ★9 ❝0 2026-10-18

VLA-Rolling: Fewer Denoising Steps, Better Control via Adaptive Action Reuse

VLA-Rolling reuses the unexecuted action tail as the starting point for denoising, cutting steps for frozen flow-matching VLAs while often raising success.

ZJU-OmniAI · Sicheng He, Yi Pan, Qiuting Yu +10

Robotics & embodied AI Efficient training & inference arXiv Code HF

#282 ▲32 ★43 ❝0 2026-10-16

DLite: History-free Speculative Decoding for Agentic AI

DLite is history-free speculative decoding that drafts locally from the target model's hidden states, suited to ever-growing agent contexts.

Shanghai Jiao Tong University · Jiaming Xu, Hanzhen Wang, Tianlang Zhao +7

Efficient training & inference Agents arXiv Code HF

#297 ▲22 ★9 ❝0 2026-10-06

Consistent Distribution Matching for Data-Free Diffusion Distillation

A data-free, simulation-free diffusion distillation where one student both generates and estimates scores, reaching strong one-step FID.

Vector Institute · Yuxiang Fu, Qi Yan, Zike Wu +4

Visual generation Efficient training & inference arXiv Code HF

#304 ▲28 2026-10-19

Kronecker Delta Rule for Long Context Linear Attention

KronLSTM introduces a Kronecker delta rule that revises matrix memory along one direction, giving stable long-context linear attention that often beats DeltaNet.

NX-AI · Anamaria-Roberta Hartl, Levente Zólyomi, Michael List +3

Efficient training & inference LLMs arXiv HF

#307 ▲22 2026-10-19

SpecKCast: Spectral Kalman Forecasting for Diffusion Acceleration

SpecKCast forecasts DiT outputs in the frequency domain with Kalman filters, running the model only when uncertainty is high, for training-free speedup.

Samsung Research · Javad Rajabi, Hakki Can Karaimer, David B. Lindell +2

Visual generation Efficient training & inference arXiv HF

Search this topic in the archive →