arXiv subjects

Yiyu Wang

Publications and source records attributed to Yiyu Wang.

At least 19 recordsLinked to original sources

arXiv2026

Grothendieck Weights on Permutohedral Varieties and Matroids

Grothendieck weights, introduced by Shah, are $K$-theoretic analogues of Minkowski weights on smooth toric varieties. We study Grothendieck weights on the permutohedral fan and prove two main results: a $K$-balancing condition that characterizes Grothendieck weights by a finite system of linear equations, and an explicit product rule for the ring structure. We apply this framework to matroids, giving a combinatorial characterization of Grothendieck weights on matroidal fans. As the main application, we compute the motivic Chern class of the hyperplane arrangement complement in its wonderful compactification and show that the result depends only on the matroid, not on the realization. This allows us to extend the definition of the motivic Chern class to all loopless matroids.

math.AG↗

arXiv2026

Grothendieck weights and K-theoretic positivity for matroids

We introduce a method for studying $K$-theoretic positivity on permutohedral toric varieties through the topology of spaces arising in tropical geometry. The key ingredient is the theory of Grothendieck weights developed by the author. We prove two positivity results using this method. The first result is the positivity of the Euler characteristics of tautological bundles associated with an arbitrary matroid and twisted by a nef line bundle. This gives numerical evidence for a conjectural vanishing theorem. The second result generalizes the external activity complex of Berget--Fink, originally defined for a pair of matroids, to the case of any tuple of matroids with no common loop. We deduce a formula for its graded $K$-polynomial in terms of exterior powers of the dual tautological quotient classes of the matroids. After a change of variables, its coefficients alternate in sign. We also prove the Cohen--Macaulayness of each such complex using the vanishing theorems for combinatorial geometries developed by Eur--Fink--Larson. This proof is new even in the case of a pair of matroids. As an application, we interpret certain Chern numbers of tautological quotient classes as counts of facets, partially answering a question of Berget--Eur--Spink--Tseng.

math.AG↗

arXiv2026

From a Static Multi-Level Small Semantic Codebook to a Dynamic Single-Level Large Semantic Codebook for Generative Recommendation

Generative recommendation represents each item with a sequence of discrete Semantic IDs (SIDs) and predicts the sequence to retrieve the next item. Typical systems use multi-level residual quantization, which increases autoregressive decoding cost and creates a large hierarchical space that may be sparsely occupied. Static codebooks also become misaligned with current traffic as new items arrive and exposure distributions change. We propose a single-level large semantic codebook that replaces multiple residual semantic codes with one semantic token while retaining a separate collaborative disambiguation token to reduce item collisions. We further introduce an exposure-aware dynamic update mechanism based on temporal weight decay, exponential moving-average center updates, and an exposure-weighted penalty on SID changes. We also develop an offline evaluation framework covering representation quality, code utilization, cluster load, full-SID collision, and temporal stability. On two public datasets, the two-level SID improves mean Recall@10 by 5.0%-8.8% and mean NDCG@10 by 4.1%-5.1% for OneRec-V1, and by 7.1%-8.7% and 3.8%-8.5%, respectively, for OneRec-V2. Dynamic updating provides further gains on KuaiRec. Across three serving architectures, the shorter SID reduces estimated autoregressive-decoding FLOPs by 47.93%-48.70% and increases single-card QPS by 28.57%-47.0%. A five-day online A/B test serving 2.5% of production traffic improves the primary consumption metric by 0.792%.

cs.IR↗

arXiv2026

OmniGameArena: A Unified UE5 Benchmark for VLM Game Agents with Improvement Dynamics

Vision-language model (VLM) agents are increasingly deployed in interactive game environments. Yet game benchmarks for VLM agents typically report a single first-attempt score per (agent, game) pair, focus on single-agent Solo play, and lack unified protocols for evaluating heterogeneous agent classes (commercial VLMs, open-weight VLMs, and specialized game policies) on the same footing. We address these gaps with OmniGameArena, a real-time benchmark of twelve newly built Unreal Engine 5 games spanning Solo (7), PvP (3), and Coop (2) with unified action interfaces, and the Improvement Dynamics Curve (IDC), an agentic-reflection harness in which a tool-using reflector LLM autonomously refines a bounded skill prompt across multiple rounds. Beyond cold-start leaderboard scores, IDC exposes two additional observables for each (agent, game) pair: how the score evolves across reflection rounds, and how the learned skill behaves on held-out task variants. We report these observables for twelve VLM agents on the cold-start leaderboard and four top agents under IDC.

cs.CV↗

arXiv2026

UxSID: Semantic-Aware User Interests Modeling for Ultra-Long Sequence

Modeling ultra-long user sequences involves a difficult trade-off between efficiency and effectiveness. While current paradigms rely on either item-specific search or item-agnostic compression, we propose UxSID, a framework exploring a third path: semantic-group shared interest memory. By utilizing Semantic IDs (SIDs) and a dual-level attention strategy, UxSID captures target-aware preferences without the heavy cost of item-specific models. This end-to-end architecture balances computational parsimony with semantic awareness, achieving state-of-the-art performance and a 0.337% revenue lift in large-scale advertising A/B test.

cs.AI↗

arXiv2026

Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods

Recent efforts to accelerate inference in Multimodal Large Language Models (MLLMs) have largely focused on visual token compression. The effectiveness of these methods is commonly evaluated by measuring the accuracy drop on existing MLLM benchmarks before and after compression. However, these benchmarks are originally designed to assess general perception and reasoning abilities, rather than the specific challenges posed by visual token compression, leading to a fundamental task mismatch. In this work, we uncover a counterintuitive yet consistent phenomenon: simple image downsampling outperforms many advanced visual token compression methods across multiple widely used benchmarks. Through a comprehensive empirical study spanning eight popular benchmarks and multiple state-of-the-art compression techniques, we show that (i) current benchmarks contain substantial noise (task-irrelevant samples) for evaluating visual token compression, and (ii) downsampling can act as an effective data filter that distinguishes between simple and difficult samples with respect to compression sensitivity. Motivated by these findings, we propose VTC-Bench, an evaluation framework that explicitly leverages downsampling as a discriminator to denoise existing benchmarks, enabling a fairer and more meaningful additional assessment of visual token compression methods.

cs.CV↗

arXiv2026

V-CAST: Video Curvature-Aware Spatio-Temporal Pruning for Efficient Video Large Language Models

Video large language models (VideoLLMs) show strong capability in video understanding, yet long-context inference is still dominated by massive redundant visual tokens in the prefill stage. We revisit token compression for VideoLLMs under a tight budget and identify a key bottleneck, namely insufficient spatio-temporal information coverage. Existing methods often introduce discontinuous coverage through coarse per-frame allocation or scene segmentation, and token merging can further misalign spatio-temporal coordinates under MRoPE-style discrete (t,h,w) bindings. To address these issues, we propose V-CAST (Video Curvature-Aware Spatio-Temporal Pruning), a training-free, plug-and-play pruning policy for long-context video inference. V-CAST casts token compression as a trajectory approximation problem and introduces a curvature-guided temporal allocation module that routes per-frame token budgets to semantic turns and event boundaries. It further adopts a dual-anchor spatial selection mechanism that preserves high-entropy visual evidence without attention intervention, while keeping retained tokens at their original coordinates to maintain positional alignment. Extensive experiments across multiple VideoLLMs of different architectures and scales demonstrate that V-CAST achieves 98.6% of the original performance, outperforms the second-best method by +1.1% on average, and reduces peak memory and total latency to 86.7% and 86.4% of vanilla Qwen3-VL-8B-Instruct.

cs.CV↗

arXiv2026

Bridging Visual Representation and Reinforcement Learning from Verifiable Rewards in Large Vision-Language Models

Reinforcement Learning from Verifiable Rewards (RLVR) has substantially enhanced the reasoning capabilities of large language models in abstract reasoning tasks. However, its application to Large Vision-Language Models (LVLMs) remains constrained by a structural representational bottleneck. Existing approaches generally lack explicit modeling and effective utilization of visual information, preventing visual representations from being tightly coupled with the reinforcement learning optimization process and thereby limiting further improvements in multimodal reasoning performance. To address this limitation, we propose KAWHI (Key-Region Aligned Weighted Harmonic Incentive), a plug-and-play reward reweighting mechanism that explicitly incorporates structured visual information into uniform reward policy optimization methods (e.g., GRPO and GSPO). The method adaptively localizes semantically salient regions through hierarchical geometric aggregation, identifies vision-critical attention heads via structured attribution, and performs paragraph-level credit reallocation to align spatial visual evidence with semantically decisive reasoning steps. Extensive empirical evaluations on diverse reasoning benchmarks substantiate KAWHI as a general-purpose enhancement module, consistently improving the performance of various uniform reward optimization methods. Project page: KAWHI (https://kawhiiiileo.github.io/KAWHI_PAGE/)

cs.CV↗

arXiv2026

Variation-aware Vision Token Dropping for Faster Large Vision-Language Models

Large vision-language models (LVLMs) have demonstrated remarkable capabilities in multimodal understanding tasks. However, the increasing demand for high-resolution image and long-video understanding results in substantial token counts, consequently leading to reduced inference efficiency. Token compression offers a direct solution by reducing the number of tokens to be processed, thereby improving computational efficiency without architectural changes. Through extensive analysis, we identify two critical limitations in existing inner-LLM token compression methods: positional bias and incompatibility with efficient operators, which critically hinder their practical deployment for LVLM acceleration. This paper presents the first approach from a dynamic token variation perspective, revealing that visual token variations within LLMs exhibit task-agnostic properties. We propose Variation-aware Vision Token Dropping (\textit{i.e.}, \textbf{V$^2$Drop}), which progressively removes visual tokens with minimal variation during LVLM inference, thereby enhancing computational efficiency. Extensive experiments across multiple models and benchmarks consistently demonstrate that V$^2$Drop maintains \textbf{94.0\%} and \textbf{98.6\%} of the original performance for image and video understanding tasks respectively, while reducing LLM generation latency by \textbf{31.5\%} and \textbf{74.2\%}.

cs.CV↗

arXiv2026

Accelerating Streaming Video Large Language Models via Hierarchical Token Compression

Streaming Video Large Language Models (VideoLLMs) have demonstrated impressive performance across various video understanding tasks, but they face significant challenges in real-time deployment due to the high computational cost of processing dense visual tokens from continuous video streams. In streaming video scenarios, the primary bottleneck lies in the Vision Transformer (ViT) encoding stage, where redundant processing of temporally similar frames leads to inefficiency. Additionally, inflated token sequences during LLM pre-filling further exacerbate latency and memory overhead. To address these challenges, we propose \textbf{S}treaming \textbf{T}oken \textbf{C}ompression (\textbf{STC}), a plug-and-play hierarchical framework that seamlessly integrates into existing streaming VideoLLMs, optimizing both ViT encoding and LLM pre-filling stages to accelerate processing. STC introduces two token-level accelerators: \textbf{STC-Cacher}, which reduces ViT encoding overhead by caching and reusing features from temporally similar frames, and \textbf{STC-Pruner}, which compresses the visual token sequence before it enters the LLM, preserving only the most salient tokens based on both spatial and temporal relevance. Extensive experiments on four baseline streaming VideoLLMs across five benchmarks demonstrate that STC outperforms other compression methods. Notably, STC retains up to \textbf{99\%} of accuracy on the ReKV framework while reducing ViT encoding latency and LLM pre-filling latency by \textbf{24.5\%} and \textbf{45.3\%}.

cs.CV↗

arXiv2026

QARM V2: Quantitative Alignment Multi-Modal Recommendation for Reasoning User Sequence Modeling

With the evolution of large language models (LLMs), there is growing interest in leveraging their rich semantic understanding to enhance industrial recommendation systems (RecSys). Traditional RecSys relies on ID-based embeddings for user sequence modeling in the General Search Unit (GSU) and Exact Search Unit (ESU) paradigm, which suffers from low information density, knowledge isolation, and weak generalization ability. While LLMs offer complementary strengths with dense semantic representations and strong generalization, directly applying LLM embeddings to RecSys faces critical challenges: representation unmatch with business objectives and representation unlearning end-to-end with downstream tasks. In this paper, we present QARM V2, a unified framework that bridges LLM semantic understanding with RecSys business requirements for user sequence modeling.

cs.IR↗

arXiv2025

Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models

Video large language models (VideoLLM) excel at video understanding, but face efficiency challenges due to the quadratic complexity of abundant visual tokens. Our systematic analysis of token compression methods for VideoLLMs reveals two critical issues: (i) overlooking distinctive visual signals across frames, leading to information loss; (ii) suffering from implementation constraints, causing incompatibility with modern architectures or efficient operators. To address these challenges, we distill three design principles for VideoLLM token compression and propose a plug-and-play inference acceleration framework "Video Compression Commander" (VidCom2). By quantifying each frame's uniqueness, VidCom2 adaptively adjusts compression intensity across frames, effectively preserving essential information while reducing redundancy in video sequences. Extensive experiments across various VideoLLMs and benchmarks demonstrate the superior performance and efficiency of our VidCom2. With only 25% visual tokens, VidCom2 achieves 99.6% of the original performance on LLaVA-OV while reducing 70.8% of the LLM generation latency. Notably, our Frame Compression Adjustment strategy is compatible with other token compression methods to further improve their performance. Our code is available at https://github.com/xuyang-liu16/VidCom2.

cs.CV↗

arXiv2025

Dolphin v1.0 Technical Report

Ultrasound is crucial in modern medicine but faces challenges like operator dependence, image noise, and real-time scanning, hindering AI integration. While large multimodal models excel in other medical imaging areas, they struggle with ultrasound's complexities. To address this, we introduce Dolphin v1.0 (V1) and its reasoning-augmented version, Dolphin R1-the first large-scale multimodal ultrasound foundation models unifying diverse clinical tasks in a single vision-language framework.To tackle ultrasound variability and noise, we curated a 2-million-scale multimodal dataset, combining textbook knowledge, public data, synthetic samples, and general corpora. This ensures robust perception, generalization, and clinical adaptability.The Dolphin series employs a three-stage training strategy: domain-specialized pretraining, instruction-driven alignment, and reinforcement-based refinement. Dolphin v1.0 delivers reliable performance in classification, detection, regression, and report generation. Dolphin R1 enhances diagnostic inference, reasoning transparency, and interpretability through reinforcement learning with ultrasound-specific rewards.Evaluated on U2-Bench across eight ultrasound tasks, Dolphin R1 achieves a U2-score of 0.5835-over twice the second-best model (0.2968) setting a new state of the art. Dolphin v1.0 also performs competitively, validating the unified framework. Comparisons show reasoning-enhanced training significantly improves diagnostic accuracy, consistency, and interpretability, highlighting its importance for high-stakes medical AI.

cs.CV↗

arXiv2025

AI for Service: Proactive Assistance with AI Glasses

In an era where AI is evolving from a passive tool into an active and adaptive companion, we introduce AI for Service (AI4Service), a new paradigm that enables proactive and real-time assistance in daily life. Existing AI services remain largely reactive, responding only to explicit user commands. We argue that a truly intelligent and helpful assistant should be capable of anticipating user needs and taking actions proactively when appropriate. To realize this vision, we propose Alpha-Service, a unified framework that addresses two fundamental challenges: Know When to intervene by detecting service opportunities from egocentric video streams, and Know How to provide both generalized and personalized services. Inspired by the von Neumann computer architecture and based on AI glasses, Alpha-Service consists of five key components: an Input Unit for perception, a Central Processing Unit for task scheduling, an Arithmetic Logic Unit for tool utilization, a Memory Unit for long-term personalization, and an Output Unit for natural human interaction. As an initial exploration, we implement Alpha-Service through a multi-agent system deployed on AI glasses. Case studies, including a real-time Blackjack advisor, a museum tour guide, and a shopping fit assistant, demonstrate its ability to seamlessly perceive the environment, infer user intent, and provide timely and useful assistance without explicit prompts.

cs.AI↗

arXiv2025

Shifting AI Efficiency From Model-Centric to Data-Centric Compression

The advancement of large language models (LLMs) and multi-modal LLMs (MLLMs) has historically relied on scaling model parameters. However, as hardware limits constrain further model growth, the primary computational bottleneck has shifted to the quadratic cost of self-attention over increasingly long sequences by ultra-long text contexts, high-resolution images, and extended videos. In this position paper, \textbf{we argue that the focus of research for efficient artificial intelligence (AI) is shifting from model-centric compression to data-centric compression}. We position data-centric compression as the emerging paradigm, which improves AI efficiency by directly compressing the volume of data processed during model training or inference. To formalize this shift, we establish a unified framework for existing efficiency strategies and demonstrate why it constitutes a crucial paradigm change for long-context AI. We then systematically review the landscape of data-centric compression methods, analyzing their benefits across diverse scenarios. Finally, we outline key challenges and promising future research directions. Our work aims to provide a novel perspective on AI efficiency, synthesize existing efforts, and catalyze innovation to address the challenges posed by ever-increasing context lengths.

cs.CL↗

arXiv2025

HEHA: Hierarchical Planning for Heterogeneous Multi-Robot Exploration of Unknown Environments

This paper considers the path planning problem for autonomous exploration of an unknown environment using multiple heterogeneous robots such as drones, wheeled, and legged robots, which have different capabilities to traverse complex terrains. A key challenge there is to intelligently allocate the robots to the unknown areas to be explored and determine the visiting order of those spaces subject to traversablity constraints, which leads to a large scale constrained optimization problem that needs to be quickly and iteratively solved every time when new space are explored. To address the challenge, we propose HEHA (Hierarchical Exploration with Heterogeneous Agents) by leveraging a recent hierarchical method that decompose the exploration into global planning and local planning. The major contribution in HEHA is its global planning, where we propose a new routing algorithm PEAF (Partial Anytime Focal search) that can quickly find bounded sub-optimal solutions to minimize the maximum path length among the agents subject to traversability constraints. Additionally, the local planner in HEHA also considers heterogeneity to avoid repeated and duplicated exploration among the robots. The experimental results show that, our HEHA can reduce up to 30% of the exploration time than the baselines.

cs.RO↗

arXiv2025

Zero-Shot Neural Architecture Search with Weighted Response Correlation

Neural architecture search (NAS) is a promising approach for automatically designing neural network architectures. However, the architecture estimation of NAS is computationally expensive and time-consuming because of training multiple architectures from scratch. Although existing zero-shot NAS methods use training-free proxies to accelerate the architecture estimation, their effectiveness, stability, and generality are still lacking. We present a novel training-free estimation proxy called weighted response correlation (WRCor). WRCor utilizes correlation coefficient matrices of responses across different input samples to calculate the proxy scores of estimated architectures, which can measure their expressivity and generalizability. Experimental results on proxy evaluation demonstrate that WRCor and its voting proxies are more efficient estimation strategies than existing proxies. We also apply them with different search strategies in architecture search. Experimental results on architecture search show that our zero-shot NAS algorithm outperforms most existing NAS algorithms in different search spaces. Our NAS algorithm can discover an architecture with a 22.1% test error on the ImageNet-1k dataset within 4 GPU hours. All codes are publicly available at https://github.com/kunjing96/ZSNAS-WRCor.git.

cs.LG↗

arXiv2025

ComfyUI-R1: Exploring Reasoning Models for Workflow Generation

AI-generated content has evolved from monolithic models to modular workflows, particularly on platforms like ComfyUI, enabling customization in creative pipelines. However, crafting effective workflows requires great expertise to orchestrate numerous specialized components, presenting a steep learning curve for users. To address this challenge, we introduce ComfyUI-R1, the first large reasoning model for automated workflow generation. Starting with our curated dataset of 4K workflows, we construct long chain-of-thought (CoT) reasoning data, including node selection, workflow planning, and code-level workflow representation. ComfyUI-R1 is trained through a two-stage framework: (1) CoT fine-tuning for cold start, adapting models to the ComfyUI domain; (2) reinforcement learning for incentivizing reasoning capability, guided by a fine-grained rule-metric hybrid reward, ensuring format validity, structural integrity, and node-level fidelity. Experiments show that our 7B-parameter model achieves a 97\% format validity rate, along with high pass rate, node-level and graph-level F1 scores, significantly surpassing prior state-of-the-art methods that employ leading closed-source models such as GPT-4o and Claude series. Further analysis highlights the critical role of the reasoning process and the advantage of transforming workflows into code. Qualitative comparison reveals our strength in synthesizing intricate workflows with diverse nodes, underscoring the potential of long CoT reasoning in AI art creation.

cs.CL↗