arXiv subjects

Zhifei Li

Publications and source records attributed to Zhifei Li.

At least 19 recordsLinked to original sources

arXiv2026

TwinPoSI: Statistical Twins for Powerful Post-Selection Inference on Population-Based Regression Coefficients

Post-selection inference (PoSI) quantifies uncertainty about regression coefficients after data-driven feature selection. A central question is the inferential target. Projection-based targets are the coefficients of the best linear approximation restricted to the selected features and depend on the selection procedure, whereas population-based targets are the selected features' coefficients in the full linear model and are often more relevant for scientific interpretation. The two targets can differ, even in sign. Existing PoSI methods largely focus on projection-based targets and may yield overly wide confidence intervals. We propose TwinPoSI (statistical twin post-selection inference), a method for powerful PoSI on population-based targets with false coverage rate (FCR) control. TwinPoSI leverages \textit{statistical twins}, defined as synthetic datasets generated from a fitted model to mimic the original data. With generating parameters known, statistical twins enable direct calibration of confidence intervals for bias introduced by data-dependent feature selection. We establish that TwinPoSI controls the FCR at the nominal level, up to Monte Carlo error and an asymptotically negligible approximation error. Moreover, in a Gaussian linear model with an orthogonal design, TwinPoSI uniquely attains the oracle average interval length to first order among the methods considered. Simulations show that TwinPoSI maintains reliable FCR control for both population-based and projection-based targets while yielding shorter confidence intervals and higher power than the competing methods. In riboflavin production data, TwinPoSI identifies associated genes, quantifies their directions and magnitudes of association, and yields the shortest average intervals among the methods considered.

stat.ME↗

arXiv2026

DINO Eats Geometry: Self-Supervised Sign Representations that Absorb Articulated Hand Geometry

Handshape and orientation are geometric components of sign language, yet many sign encoders learn from appearance alone. We introduce SignDEG (DINO Eats Geometry), a temporal sign encoder that uses articulated hand geometry as a pre-training target and requires only video at inference. Frozen DINOv3 features of tracked hands and faces feed per-stream temporal Transformers. Geometric latent prediction (GLP) supervises an intermediate block with WiLoR latents, MANO articulation, and 3D joints, including at masked frames. Geometric relation transfer (GRT) matches cross-video frame-similarity distributions at the final block. Both objectives are learned jointly with temporal self-distillation; WiLoR and the geometry heads are then discarded. Under the SHuBERT public-data evaluation protocol, SignDEG reaches 17.9/24.5 BLEU-4 on How2Sign/OpenASL, compared with 16.2/23.2 for SHuBERT. Rank-1 adaptation improves ASL Citizen and Sem-Lex recognition by 0.02 Recall@1 each, and phonological classification improves across 16 attributes. Removing GRT while retaining GLP reduces How2Sign BLEU-4 by 1.4 and ASL Citizen Recall@1 by 0.034. The results support transferring articulated structure into an appearance encoder without running a hand reconstruction model at deployment.

cs.CV↗

arXiv2026

More Perspectives, Stronger Signals: Multi-Perspective Enhancement and Progressive Fusion for Multimodal Entity Representation Learning

Learning effective multimodal entity representations is fundamental for reasoning tasks such as multimodal knowledge graph completion (MMKGC). However, existing methods often suffer from semantic over-smoothing within modalities and ineffective noise filtration across modalities, particularly under sparse or ambiguous conditions. To overcome these limitations, we propose PrismF, a unified framework that synergizes multi-perspective enhancement with progressive fusion to extract stronger signals from diverse inputs. PrismF enhances fine-grained intra-modal semantics through a multi-perspective mechanism that decomposes each modality into complementary views and constrains them with a decoupling loss to reduce representation collapse. Furthermore, it improves cross-modal integration through a progressive fusion strategy that dynamically calibrates inter-modal interactions, enabling the model to emphasize informative signals while suppressing noisy or unreliable ones. Extensive experiments on three public benchmarks show that PrismF achieves the strongest overall performance, including relative improvements of 4.04% in MRR and 11.17% in Hits@1 on KVC16K. Our code can be found at https://github.com/HubuKG/PrismF.

cs.AI↗

arXiv2026

PIXELRAG: Web Screenshots Beat Text for Retrieval-Augmented Generation

Augmenting large language models (LLMs) with retrieved web text has become a dominant paradigm, yet the web is not natively textual: existing systems depend on complex parsing pipelines that linearize HTML and discard layout, visual structure, and formatting. We introduce PixelRAG, a new retrieval-augmented method that represents websites in their native visual form and performs retrieval and reading entirely in pixel space, enabling an end-to-end architecture that eliminates text abstraction. PixelRAG is, to our knowledge, the first pipeline to operate over a full Wikipedia corpus in this form, scaling to a datastore of 30 million screenshot images with an efficient visual retrieval index. Built on an existing visual embedding model (i.e., Qwen3-VL-Embedding), PixelRAG further fine-tunes this model on screenshot data with carefully curated contrastive training data. Retrieved screenshots are then fed directly as pixel inputs to a VLM, without intermediate text conversion. PixelRAG consistently outperforms both no-retrieval and text-based RAG baselines, most surprisingly on widely studied text-centric tasks such as NQ and SimpleQA. It also achieves strong gains on multimodal open-domain QA (e.g., MMSearch), benchmarks over noisy news corpora (e.g., LiveVQA), and agentic benchmarks (e.g., MoNaCo), improving accuracy by up to 18.1% over text-based baselines. Finally, pixel representations enable a new efficiency lever for RAG through image compression, achieving up to 3x token cost reduction at lower resolutions while maintaining accuracy. Our results challenge the necessity of text representations in web retrieval, suggesting that web RAG can operate directly in the web's native visual form while improving both performance and efficiency.

cs.IR↗

arXiv2026

Idleness is Relative: Exploiting Tool-Call Idle Windows for Offloading in Agentic Systems with MORI

Modern LLM serving systems increasingly host agentic workloads, whose sessions issue tens of model invocations interleaved with tool calls, accumulating KV cache that can be reused across steps. As requests' total KV cache size easily exceeds GPU HBM capacity, researchers offload them to CPU DRAM. However, tool-call durations span orders of magnitude, and the cost of transferring KV cache between tiers makes it impractical to re-place entries on every call. We observe that agentic programs exhibit a two-phase structure: busy phases of rapid short tool calls and idle phases dominated by long-running calls. Current eviction policies such as LRU fail to capture this property. A binary busy/idle label also falls short because the ratio of busy to idle programs may not match the hardware's GPU-to-CPU capacity ratio. When it does not, one tier sits underutilized while the other is oversubscribed, wasting memory or forcing unnecessary evictions. We present MORI, an agent serving system that solves the above problem. Our key insight is that idleness is a continuous, relative spectrum. MORI ranks all active programs by idleness, assigns the busiest to GPU HBM and the most idle to CPU DRAM, dynamically shifts the partition boundary to match hardware capacity, and enforces admission control at each memory tier. Evaluated on real coding agent workloads collected from Claude Code across four GPU and model pairs, MORI delivers 20--71% higher throughput and 18--43% lower TTFT than the best baseline with offloading.

cs.OS↗

arXiv2026

HyLoVQA: Dynamic Hypernetwork-Generated Low-Rank Adaptation for Continual Visual Question Answering

Continual Visual Question Answering (VQA) requires learning from non-stationary streams of visual inputs and questions while preserving past knowledge. Most prior methods adapt by updating a largely shared parameter set. This often leads to cross-level task interference, hindering accurate adaptation to the current task and object. To address this limitation, we propose HyLoVQA. It maintains a drift-resilient memory bank of anchors. The bank stores the content of visual objects and textual tasks, and they are updated using current input features. Conditioned on retrieved anchors, a hypernetwork generates lightweight Low-Rank Adaptation (LoRA) adapters. This ensures parameter efficiency, allowing the model to adapt to each task and object dynamically. Additionally, we formulate an alignment loss that aligns semantic discrepancies in the feature space with functional changes in the parameter space, thereby constraining LoRA adapters to remain focused on the current task and object. Extensive experiments on VQA v2 and NExT-QA under both standard and compositional settings demonstrate the superiority of HyLoVQA over prior state-of-the-art methods.

cs.CV↗

arXiv2026

Modality-Aware Identity Construction and Counterfactual Structure Learning for ID-Free Multimodal Recommendation

Multimodal recommendation has attracted extensive attention by leveraging heterogeneous modality information to alleviate data sparsity and improve recommendation accuracy. Existing methods have attempted to replace ID embeddings with multimodal features and have achieved promising preliminary results. However, these methods still exhibit the following two limitations: (1) the reconstructed ID representations remain relatively static and fail to fully exploit multimodal semantics; and (2) the graph learning process is insufficient in mining latent long-tail semantic relations and is easily affected by popularity bias. To address these issues, we propose a novel method named Modality-Aware Identity Construction and Counterfactual Structure Learning for ID-free Multimodal Recommendation (MAIL). Specifically, we design a modality-aware identity construction module that dynamically modulates positional encodings with multimodal semantics to construct content-aware ID-free identity representations. Then, we propose a counterfactual structure learning paradigm that mines low-exposure semantic neighbors via popularity penalization and alleviates popularity bias. Extensive experiments are conducted on five public Amazon datasets. Experimental results show that MAIL achieves average improvements of 7.81% in Recall@10 and 12.81% in NDCG@10 compared with the baseline models. Our code is available at https://github.com/HubuKG/MAIL.

cs.IR↗

arXiv2026

Advancing MAPF Toward the Real World: A Scalable Multi-Agent Realistic Testbed (SMART)

We present Scalable Multi-Agent Realistic Testbed (SMART), a realistic and efficient software tool for evaluating Multi-Agent Path Finding (MAPF) algorithms. MAPF focuses on planning collision-free paths for a group of robots. While state-of-the-art MAPF planners can plan paths for hundreds of robots in seconds, they often rely on simplified robot models, making their real-world performance unclear. Researchers typically lack access to hundreds of physical robots in laboratory settings to evaluate the algorithms. Meanwhile, industrial professionals who lack expertise in MAPF require an easy-to-use simulator to efficiently test and understand the performance of MAPF planners in their specific settings. SMART fills this gap with several advantages: (1) SMART uses physics-engine-based simulators to create realistic simulation environments, accounting for complex real-world factors such as robot kinodynamics and execution uncertainties, (2) SMART uses an execution monitor framework based on the Action Dependency Graph, facilitating seamless integration with various MAPF planners and robot models, and (3) SMART scales to thousands of robots. The code is publicly available at https://github.com/smart-mapf/smart with an online service available at https://smart-mapf.github.io/demo/.

cs.RO↗

arXiv2026

CocoaBench: Evaluating Unified Digital Agents in the Wild

LLM agents now perform strongly in software engineering, deep research, GUI automation, and various other applications, while recent agent scaffolds and models are increasingly integrating these capabilities into unified systems. Yet, most evaluations still test these capabilities in isolation, which leaves a gap for more diverse use cases that require agents to combine different capabilities. We introduce CocoaBench, a benchmark for unified digital agents built from human-designed, long-horizon tasks that require flexible composition of vision, search, and coding. Tasks are specified only by an instruction and an automatic evaluation function over the final output, enabling reliable and scalable evaluation across diverse agent infrastructures. We also present CocoaAgent, a lightweight shared scaffold for controlled comparison across model backbones. Experiments show that current agents remain far from reliable on CocoaBench, with the best evaluated system achieving only 45.1% success rate. Our analysis further points to substantial room for improvement in reasoning and planning, tool use and execution, and visual grounding.

cs.CL↗

arXiv2026

Analyzing Planner Design Trade-offs for MAPF under ADG-based Realistic Execution

Multi-Agent Path Finding (MAPF) algorithms are increasingly deployed in industrial warehouses and automated manufacturing facilities, where robots must operate reliably under real-world physical constraints. However, existing MAPF evaluation frameworks typically rely on simplified robot models, leaving a substantial gap between algorithmic benchmarks and practical performance. Recent frameworks such as SMART combine kinodynamic modeling with execution based on the Action Dependency Graph (ADG), enabling realistic, large-scale MAPF evaluation. Building on this capability, this work investigates how key planner design choices influence performance under realistic execution settings. We systematically study three fundamental factors: (1) the relationship between solution optimality and execution performance, (2) the sensitivity of system performance to inaccuracies in kinodynamic modeling, and (3) the tradeoff between model accuracy and plan optimality. Empirically, we examine these factors to understand how these design choices affect performance in realistic scenarios. We highlight open challenges and research directions to steer the community toward practical, real-world deployment.

cs.AI↗

arXiv2026

EvoX: Meta-Evolution for Automated Discovery

Recent work such as AlphaEvolve has shown that combining LLM-driven optimization with evolutionary search can effectively improve programs, prompts, and algorithms across domains. In this paradigm, previously evaluated solutions are reused to guide the model toward new candidate solutions. Crucially, the effectiveness of this evolution process depends on the search strategy: how prior solutions are selected and varied to generate new candidates. However, most existing methods rely on fixed search strategies with predefined knobs (e.g., explore-exploit ratios) that remain static throughout execution. While effective in some settings, these approaches often fail to adapt across tasks, or even within the same task as the search space changes over time. We introduce EvoX, an adaptive evolution method that optimizes its own evolution process. EvoX jointly evolves candidate solutions and the search strategies used to generate them, continuously updating how prior solutions are selected and varied based on progress. This enables the system to dynamically shift between different search strategies during the optimization process. Across nearly 200 real-world optimization tasks, EvoX outperforms existing AI-driven evolutionary methods including AlphaEvolve, OpenEvolve, GEPA, and ShinkaEvolve on the majority of tasks.

cs.LG↗

arXiv2026

MyGram: Modality-aware Graph Transformer with Global Distribution for Multi-modal Entity Alignment

Multi-modal entity alignment aims to identify equivalent entities between two multi-modal Knowledge graphs by integrating multi-modal data, such as images and text, to enrich the semantic representations of entities. However, existing methods may overlook the structural contextual information within each modality, making them vulnerable to interference from shallow features. To address these challenges, we propose MyGram, a modality-aware graph transformer with global distribution for multi-modal entity alignment. Specifically, we develop a modality diffusion learning module to capture deep structural contextual information within modalities and enable fine-grained multi-modal fusion. In addition, we introduce a Gram Loss that acts as a regularization constraint by minimizing the volume of a 4-dimensional parallelotope formed by multi-modal features, thereby achieving global distribution consistency across modalities. We conduct experiments on five public datasets. Results show that MyGram outperforms baseline models, achieving a maximum improvement of 4.8% in Hits@1 on FBDB15K, 9.9% on FBYG15K, and 4.3% on DBP15K.

cs.AI↗

arXiv2026

SkyNomad: On Using Multi-Region Spot Instances to Minimize AI Batch Job Cost

AI batch jobs such as model training, inference pipelines, and data analytics require substantial GPU resources and often need to finish before a deadline. Spot instances offer 3-10x lower cost than on-demand instances, but their unpredictable availability makes meeting deadlines difficult. Existing systems either rely solely on spot instances and risk deadline violations, or operate in simplified single-region settings. These approaches overlook substantial spatial and temporal heterogeneity in spot availability, lifetimes, and prices. We show that exploiting such heterogeneity to access more spot capacity is the key to reduce the job execution cost. We present SkyNomad, a multi-region scheduling system that maximizes spot usage and minimizes cost while guaranteeing deadlines. SkyNomad uses lightweight probing to estimate availability, predicts spot lifetimes, accounts for migration cost, and unifies regional characteristics and deadline pressure into a monetary cost model that guides scheduling decisions. Our evaluation shows that SkyNomad achieves 1.25-3.96x cost savings in real cloud deployments and performs within 10% cost differences of an optimal policy in simulation, while consistently meeting deadlines.

cs.DC↗

arXiv2026

MacVQA: Adaptive Memory Allocation and Global Noise Filtering for Continual Visual Question Answering

Visual Question Answering (VQA) requires models to reason over multimodal information, combining visual and textual data. With the development of continual learning, significant progress has been made in retaining knowledge and adapting to new information in the VQA domain. However, current methods often struggle with balancing knowledge retention, adaptation, and robust feature representation. To address these challenges, we propose a novel framework with adaptive memory allocation and global noise filtering called MacVQA for visual question answering. MacVQA fuses visual and question information while filtering noise to ensure robust representations, and employs prototype-based memory allocation to optimize feature quality and memory usage. These designs enable MacVQA to balance knowledge acquisition, retention, and compositional generalization in continual VQA learning. Experiments on ten continual VQA tasks show that MacVQA outperforms existing baselines, achieving 43.38% average accuracy and 2.32% average forgetting on standard tasks, and 42.53% average accuracy and 3.60% average forgetting on novel composition tasks.

cs.CV↗

arXiv2025

Let the Barbarians In: How AI Can Accelerate Systems Performance Research

Artificial Intelligence (AI) is beginning to transform the research process by automating the discovery of new solutions. This shift depends on the availability of reliable verifiers, which AI-driven approaches require to validate candidate solutions. Research focused on improving systems performance is especially well-suited to this paradigm because system performance problems naturally admit such verifiers: candidates can be implemented in real systems or simulators and evaluated against predefined workloads. We term this iterative cycle of generation, evaluation, and refinement AI-Driven Research for Systems (ADRS). Using several open-source ADRS instances (i.e., OpenEvolve, GEPA, and ShinkaEvolve), we demonstrate across ten case studies (e.g., multi-region cloud scheduling, mixture-of-experts load balancing, LLM-based SQL, transaction scheduling) that ADRS-generated solutions can match or even outperform human state-of-the-art designs. Based on these findings, we outline best practices (e.g., level of prompt specification, amount of feedback, robust evaluation) for effectively using ADRS, and we discuss future research directions and their implications. Although we do not yet have a universal recipe for applying ADRS across all of systems research, we hope our preliminary findings, together with the challenges we identify, offer meaningful guidance for future work as researcher effort shifts increasingly toward problem formulation and strategic oversight. Note: This paper is an extension of our prior work [14]. It adds extensive evaluation across multiple ADRS frameworks and provides deeper analysis and insights into best practices.

cs.SE↗

arXiv2025

KeenKT: Knowledge Mastery-State Disambiguation for Knowledge Tracing

Knowledge Tracing (KT) aims to dynamically model a student's mastery of knowledge concepts based on their historical learning interactions. Most current methods rely on single-point estimates, which cannot distinguish true ability from outburst or carelessness, creating ambiguity in judging mastery. To address this issue, we propose a Knowledge Mastery-State Disambiguation for Knowledge Tracing model (KeenKT), which represents a student's knowledge state at each interaction using a Normal-Inverse-Gaussian (NIG) distribution, thereby capturing the fluctuations in student learning behaviors. Furthermore, we design an NIG-distance-based attention mechanism to model the dynamic evolution of the knowledge state. In addition, we introduce a diffusion-based denoising reconstruction loss and a distributional contrastive learning loss to enhance the model's robustness. Extensive experiments on six public datasets demonstrate that KeenKT outperforms SOTA KT models in terms of prediction accuracy and sensitivity to behavioral fluctuations. The proposed method yields the maximum AUC improvement of 5.85% and the maximum ACC improvement of 6.89%.

cs.AI↗

arXiv2025

FrontierCS: Evolving Challenges for Evolving Intelligence

We introduce FrontierCS, a benchmark of 156 open-ended problems across diverse areas of computer science, designed and reviewed by experts, including CS PhDs and top-tier competitive programming participants and problem setters. Unlike existing benchmarks that focus on tasks with known optimal solutions, FrontierCS targets problems where the optimal solution is unknown, but the quality of a solution can be objectively evaluated. Models solve these tasks by implementing executable programs rather than outputting a direct answer. FrontierCS includes algorithmic problems, which are often NP-hard variants of competitive programming problems with objective partial scoring, and research problems with the same property. For each problem we provide an expert reference solution and an automatic evaluator. Combining open-ended design, measurable progress, and expert curation, FrontierCS provides a benchmark at the frontier of computer-science difficulty. Empirically, we find that frontier reasoning models still lag far behind human experts on both the algorithmic and research tracks, that increasing reasoning budgets alone does not close this gap, and that models often over-optimize for generating merely workable code instead of discovering high-quality algorithms and system designs.

cs.LG↗

arXiv2025

LEANN: A Low-Storage Vector Index

Embedding-based vector search underpins many important applications, such as recommendation and retrieval-augmented generation (RAG). It relies on vector indices to enable efficient search. However, these indices require storing high-dimensional embeddings and large index metadata, whose total size can be several times larger than the original data (e.g., text chunks). Such high storage overhead makes it difficult, or even impractical, to deploy vector search on personal devices or large-scale datasets. To tackle this problem, we propose LEANN, a storage-efficient index for vector search that recomputes embeddings on the fly instead of storing them, and compresses state-of-the-art proximity graph indices while preserving search accuracy. LEANN delivers high-quality vector search while using only a fraction of the storage (e.g., 5% of the original data) and supporting storage-efficient index construction and updates. On real-world benchmarks, LEANN reduces index size by up to 50x compared with conventional indices, while maintaining SOTA accuracy and comparable latency for RAG applications.

cs.DB↗