#efficient inference

14 results
cs.CV2026

Calibrate Before Reason: Robust Visual Token Reduction against Semantic Drift in VLMs

Jiasheng Li, Zhong Ji, Yan Zhang +1

The paper proposes CaRe, a training‑free method that calibrates compact visual representations before reasoning to keep semantic consistency when reducing visual tokens in large vi…

#visual token reduction#vision-language models#semantic drift#model calibration
cs.CV2026

Finding Change in Satellite Archives from Text: How to Combine Before-and-After Images Efficiently

Simon Roy, Mark Bong, Giovanni Beltrame

The paper studies how to efficiently combine before-and-after satellite images to match natural‑language change queries, comparing attention, state‑space (Mamba), and compressed fu…

#satellite imagery#change detection#text‑image retrieval#fusion architectures
cs.CV2026

ObjectStream: Latent Objects as Memory Anchors for Streaming Video Understanding

Mingkang Dong, Muxin Pu, Jie Li +8

ObjectStream introduces a training‑free method that extracts latent objects from frozen Video‑LLM representations and uses them as persistent memory anchors to improve streaming vi…

#video streaming#object-centric memory#large language models#latent objects
cs.AI2026

Penelope: Localized Latent Recurrence for Efficient Structured Reasoning

Yutong Chen, Shouqian Shi, Xinran Liu +5

Penelope introduces a method that adds a localized recurrent computation within a decoder-only Transformer to perform structured reasoning efficiently, using a latent space instead…

#structured reasoning#latent reasoning#decoder-only transformers#efficient inference
cs.RO2026

GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch

GigaWorld Team, Angen Ye, Angyuan Ma +26

The paper introduces GigaWorld-Policy-0.5, a robot control model that learns from future visual dynamics during training but generates actions only at inference, achieving faster (…

#robot control#world action models#action-conditioned world modeling#efficient inference
cs.CV2026

VideoSEMA: a scalable and efficient Mamba-like attention for video understanding

Nhat Thanh Tran, Fanghui Xue andShuai Zhang, Fanghui Xue +5

The paper introduces VideoSEMA, a split space‑time attention model for video classification that combines a scalable Mamba‑like spatial attention block with softmax temporal attent…

#video classification#attention mechanisms#mamba architecture#spatial-temporal modeling
cs.CV2026

Attention-Free and Lightweight Token Reduction for Efficient Vision-Language Models

Xuanyi Hao, Zuoyuan Zhang, Zhibo Wang +4

The paper introduces a plug‑and‑play, attention‑free token reduction module for vision‑language models that selects informative and diverse visual tokens using an entropy‑based imp…

#vision-language models#token reduction#attention-free#entropy-based selection
cs.DC2026

FlashDiff: Efficient Regional Execution and Scheduling for Diffusion Model Serving

Yaqi Qiao, Ping He, Songrun Xie +4

FlashDiff is a system that speeds up diffusion model inference by dynamically selecting which latent regions need further processing and efficiently scheduling those regions across…

#diffusion models#model serving#regional execution#GPU scheduling
cs.IR2026

SlimPer: Make Personalization Model Slim and Smart

Siqi Wang, Xianjie Chen, Shaofeng Deng +42

SlimPer is a transformer‑based recommendation model that treats personalized ranking as iterative refinement of a compact user‑item knowledge base, achieving linear per‑layer cost…

#recommendation systems#personalization#transformer models#efficient inference
cs.LG2026

AVQ-Attention: Adaptive Vector-Quantized Attention

Winfried van den dool, Patrick Forré, Amir Habibian +2

The paper introduces Adaptive Vector-Quantized (AVQ) Attention, which dynamically allocates codebook capacity to the most important regions of the key space, preserving O(MN) compl…

#transformers#attention mechanisms#vector quantization#efficient inference
cs.LG2026

EMAGN: Efficient Multi-Attention Graph Network via Learned Clustering for Scalable Traffic Forecasting

Mingxing Xu, Rakesh Chowdary Machineni, Ke Liu +7

The paper introduces EMAGN, a graph neural network that uses learned clustering to linearize multi-head attention, enabling scalable traffic forecasting with reduced computation an…

#traffic forecasting#graph neural networks#attention mechanisms#efficient inference
cs.AI2026

Recursive Multi-Agent Systems

Jiaru Zou, Rui Pan, Ruizhong Qiu +8

The paper proposes RecursiveMAS, a framework that treats a multi-agent system as a recursive latent‑space computation, enabling agents to iteratively refine each other's thoughts a…

#multi-agent systems#recursive computation#language models#collaborative AI
cs.LG2026

Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers

Ying Fan, Anej Svete, Kangwook Lee

The paper introduces LOTUS, a looped Transformer architecture that performs multi-step reasoning in latent space, achieving reasoning performance comparable to explicit chain-of-th…

#latent reasoning#chain-of-thought#looped transformers#efficient inference
cs.AI2026

Mobility-Aware Cache Framework for Scalable LLM-Based Human Mobility Simulation

Hua Yan, Heng Tan, Yingxue Zhang +1

The paper introduces MobCache, a mobility-aware caching framework that stores and reuses latent-space embeddings of LLM reasoning steps to enable efficient large-scale human mobili…

#human mobility simulation#large language models#caching#latent embeddings