arXiv subjects

Yao Tian

Publications and source records attributed to Yao Tian.

At least 19 recordsLinked to original sources

arXiv2026

HearInContext: A Benchmark for Implicit Context in Speech Recognition

Contextual ASR can benefit from semantic cues or from target words explicitly provided in the context. We introduce HearInContext, a Mandarin--English benchmark that pairs shared synthetic speech with assistant replies supporting different interpretations. The benchmark comprises 3,764 semantic test cases built around homophones. Implicit contexts exclude candidate words; explicit contexts name the target. No-context and unrelated-context controls measure the benefit of relevant history and sensitivity to irrelevant history. Context-capable models benefit from implicit cues but achieve higher target recall with explicit hints. Fine-tuning Qwen3-ASR-1.7B improves implicit-context target recall by 11.0 and 11.5 percentage points in Mandarin and English, respectively, while absolute CER/WER changes on AISHELL-1 and LibriSpeech remain below 0.1 percentage points. Gains extend to explicit conditions excluded from fine-tuning and to Mandarin hotword recognition on real recordings.

cs.CL↗

arXiv2026

Unified Vision-Centric Pedestrian Crossing Action Prediction via Adaptive Patch Projection and Proactive Spatial Rectification

Vision cues are available and informative for pedestrian action prediction, but obtaining stable target-centric representations from video frames remains challenging without frame-level external perception cues. Thus, most methods rely on additional perception modules or multi-source information fusion, leaving the reliability of vision-centric setting an open question. To this end, we propose ViCross, a vision-centric pedestrian crossing action prediction framework powered by multimodal large language models, which maintains target-centric reasoning from video frames without additional perception modules beyond first-frame target initialization. While multimodal large language models exhibit strong visual understanding, applying them directly to vision-centric action prediction faces two challenges. First, accurately perceiving target pedestrians often requires high resolution inputs and dense visual tokenization, making full-frame encoding computationally prohibitive. ViCross tackles this with Variable Resolution Patch Mapping module for efficient token allocation while preserving key pedestrian details. Second, missing spatiotemporal priors hinder consistent cross frame reasoning. ViCross mitigates this with a Spatial Constraint Enhancement Strategy that captures past motion, future locations, and action semantics for training-time proactive spatial rectification. Extensive experiments show that ViCross delivers clear gains in vision-centric prediction settings and is competitive with multi-source fusion approaches in several settings. Code is available at https://github.com/2tianyao1/ViCross.git.

cs.CV↗

arXiv2026

RW-TTT: Batched Serving for Request-Owned Test-Time Training State

Test-time training (TTT) adapts an LLM during generation by reading and updating request-owned state, such as fast weights, low-rank deltas, or streaming learner state. This breaks batched LLM serving, which assumes shared static weights: serial execution is correct but slow, while naive batching can corrupt request state. We formulate this problem as read-write TTT serving and present RW-TTT , which tags each decode step with its owner, version, and READ/WRITE effect, batches only compatible phases, and commits updates only to the owner. On one GPU with eight fast-weight InPlace-TTT streams, RW-TTT reaches 274.61 aggregate tok/s, 9.31x over sequential serving and 3.44x over per-stream replicas under the same memory budget. It preserves behavior on RULER, a long-context benchmark, and passes owner/version checks.

cs.LG↗

arXiv2026

ByteX: A Unified AI Search Engine at ByteDance

Since 2016, ByteX has been the foundation of ByteDance's search infrastructure, scaling to more than 7,000 clusters and 300 PB of indexed data. Driven by the demands of AI workloads, ByteX has evolved from a text search engine into a unified AI search system supporting vector retrieval, lexical matching, and predicate filtering. Its largest deployment indexes nearly one trillion high-dimensional vectors. This scale exposes two central bottlenecks in AI-era retrieval: memory-intensive graph-index construction under sustained ingestion, and the prohibitive cost of keeping vector indexes entirely in memory. ByteX addresses these bottlenecks with two techniques. First, it introduces a quantization-aware vector kernel based on SymRaBitQ, a new symmetric quantization scheme with tight theoretical guarantees that allows index construction to run directly in the quantized space accurately and efficiently without retaining a copy of full-precision vectors. Second, it provides a hybrid storage engine that supports memory-resident, hybrid, and SSD-resident deployments, with fine-grained record-level caching to trade memory for latency under operational control. On large-scale benchmarks, ByteX improves throughput by up to 3x, reduces indexing memory by 80%, and lowers operating cost by 86% compared with prior systems, while supporting trillion-vector scale, write-heavy or latency-sensitive workloads in production.

cs.DB↗

arXiv2026

Beyond Retrieval: Analytic Memory for Multimodal Agents

Long-term multimodal memory must support not only retrieving relevant information but also computing over observations accumulated across interactions. Existing systems largely emphasize \emph{retrieval memory}, organizing interaction histories through summaries and indexes to return query-relevant information at multiple granularities, from high-level abstractions to underlying records. In this paper, we formulate \emph{analytic memory} as a complementary abstraction that organizes recurring multimodal observations into queryable structures supporting filtering, aggregation, ranking, and temporal comparison. We present AdaMM, a framework that jointly supports retrieval and analytic memory. Rather than relying on application-defined schemas, AdaMM extracts provenance-linked attribute-value observations from dialogue, images, and contextual metadata, discovers recurring field structures, and materializes them for analytical access. At inference time, a memory-aware planner decomposes queries into retrieval and analytic operations and routes each operation to the appropriate tools. Experiments on two long-term multimodal memory benchmarks, MemEye and MemGallery, show that AdaMM improves performance by up to 11.3\% and 6.9\%, respectively.

cs.AI↗

arXiv2026

DocNavRAG: Document-Structured Graph RAG with Stateful Evidence Construction for Complex Document Question Answering

Answering complex questions over large document collections requires assembling complementary evidence across sections and documents. GraphRAG offers structured retrieval but typically uses fixed traversal, while agentic RAG operates over weakly structured interfaces. Our key insight is that agents should navigate document structure within and across documents rather than repeatedly search from scratch. We introduce DocNavRAG, which organizes document hierarchies and cross-region relations into a navigable graph, exposes graph operations for locating, navigating, expanding, and fetching, and maintains an evolving evidence state to guide retrieval until sufficient evidence is collected. Across four long- and multi-document QA benchmarks, DocNavRAG improves answer quality and context sufficiency over the strongest baseline by 7.8\% and 17.7\% on average.

cs.CL↗

arXiv2026

Hidden-Domain Routing for All-Type Audio Deepfake Detection

All-type audio deepfake detection requires authenticity decisions across speech, environmental sound, singing voice, and music, while the audio type is unavailable at inference time. In AT-ADD Track2, this setting creates a hidden audio-domain condition: the binary real/fake label is shared across domains, but representation structure and detector-score behavior vary with audio type. We present a closed-condition routed system that first recovers the hidden audio domain and then interprets detector scores within the selected branch. The AudioType-BEATs-6s Router estimates audio type from a 6-second window; speech inputs are handled by the Speech-XLSR Expert, while sound, singing, and music rely on EAT-based general-audio experts with branch-local score interpretation. Development-set representation analysis, router-family comparisons, and component results show audio-domain separation and complementary detector strengths across audio types. On the official AT-ADD Track2 final evaluation, the system achieves 96.10% Track2 Macro-F1 and ranks first on the final leaderboard, with type-wise Macro-F1 scores of 88.07%, 98.18%, 99.07%, and 99.08% for speech, sound, singing, and music, respectively. These results support recovering the hidden audio domain before interpreting detector scores in all-type audio deepfake detection.

cs.SD↗

arXiv2026

WhisperVC: Decoupled Cross-Domain Alignment and Speech Generation for Low-Resource Whisper-to-Normal Conversion

Whispered speech lacks vocal-fold excitation, making intelligible conversion challenging. We propose WhisperVC, a three-stage framework for low-resource whisper-to-normal (W2N) conversion that decouples cross-domain alignment from speech generation. Stage 1 uses limited paired whisper-normal data with a content encoder and a Conformer-based variational autoencoder (VAE) with soft-DTW alignment to learn domain-invariant semantic representations. Stage 2, trained only on normal speech, employs a Length-Channel Aligner and a two-stage speaker-conditioned mel generator for timbre and prosody modeling. Stage 3 fine-tunes a HiFi-GAN vocoder for waveform synthesis. Experimental results on AISHELL6-Whisper show competitive quality (DNSMOS 3.07, UTMOS 2.83, CER 16.93%) and WavLM speaker similarity (0.95). The framework also supports privacy-preserving communication as well as non-vocal communication and a rehabilitation tool for post-surgical vocal-fold patients. Samples are available online.

eess.AS↗

arXiv2026

VisualNeo: Bridging the Gap between Visual Query Interfaces and Graph Query Engines

Visual Graph Query Interfaces (VQIs) empower non-programmers to query graph data by constructing visual queries intuitively. Devising efficient technologies in Graph Query Engines (GQEs) for interactive search and exploration has also been studied for years. However, these two vibrant scientific fields are traditionally independent of each other, causing a vast barrier for users who wish to explore the full-stack operations of graph querying. In this demonstration, we propose a novel VQI system built upon Neo4j called VisualNeo that facilities an efficient subgraph query in large graph databases. VisualNeo inherits several advanced features from recent advanced VQIs, which include the data-driven gui design and canned pattern generation. Additionally, it embodies a database manager module in order that users can connect to generic Neo4j databases. It performs query processing through the Neo4j driver and provides an aesthetic query result exploration.

cs.DB↗

arXiv2026

In-orbit Test of the Weak Equivalence Principle with Atom Interferometry

The Weak Equivalence Principle (WEP) is a central pillar of general relativity. Its precise test with quantum systems in space offers a unique window onto new physics. Here we report the first in-orbit quantum test of the WEP. A dual-species (85Rb/87Rb) atom interferometer is realized aboard the China Space Station. Methods of platform motion suppression, fluorescence detection switching, and two-photon detuning switching are developed to eliminate phase noise and improve measurement accuracy. A test uncertainty of 2.8*10-8 is obtained from 280 days of WEP test data, and a test result of (-3.1+/-4.6)*10-7 is achieved after error estimation. This improves prior atom-interferometric WEP tests in microgravity by three orders of magnitude. This work paves the way for space-borne quantum inertial sensors and their application to future fundamental physics in space.

physics.atom-ph↗

arXiv2026

GEM: A Native Graph-based Index for Multi-Vector Retrieval

In multi-vector retrieval, both queries and data are represented as sets of high-dimensional vectors, enabling finer-grained semantic matching and improving retrieval quality over single-vector approaches. However, its practical adoption is held back by the lack of effective indexing algorithms. Existing work, attempting to reuse standard single-vector indexes, often fails to preserve multi-vector semantics or remains slow. In this work, we present GEM, a native indexing framework for multi-vector representations. The core idea is to construct a proximity graph directly over vector sets, preserving their fine-grained semantics while enabling efficient navigation. First, GEM designs a set-level clustering scheme. It associates each vector set with only its most informative clusters, effectively reducing redundancy without hurting semantic coverage. Then, it builds local proximity graphs within clusters and bridges them into a globally navigable structure. To handle the non-metric nature of multi-vector similarity, GEM decouples the graph construction metric from the final relevance score and injects semantic shortcuts to guide efficient navigation toward relevant regions. At query time, GEM launches beam search from multiple entry points and prunes paths early using cluster cues. To further enhance efficiency, a quantized distance estimation technique is used for both indexing and search. Across in-domain, out-of-domain, and multi-modal benchmarks, GEM achieves up to 16x speedup over state-of-the-art methods while matching or improving accuracy.

cs.IR↗

arXiv2026

Robust Audio-Visual Target Speaker Extraction with Emotion-Aware Multiple Enrollment Fusion

Audio-Visual Target Speaker Extraction (AVTSE) is crucial for cocktail party scenarios. Leveraging multiple cues --such as utterance-level speaker embeddings or steady face images, and frame-level lip motion or facial expression features --can significantly improve performance. However, real-world applications often suffer from intermittent signal loss, especially for frame-level cues. This paper systematically investigates the robustness of multi-enrollment fusion under varying degrees of modality missing. Results show that while full multimodal fusion excels under ideal conditions, its performance degrades sharply when encountering unseen modalities missing during the testing. Crucially, training with a high missing rate dramatically enhances robustness, maintaining stable performance even under severe test-time modality missing. We demonstrate that fusing the complementary one frame of face image with frame-level lip features achieves both strong performance and robustness for the AVTSE task. The model and codes are shared.

eess.AS↗

arXiv2026

Optimizing SSD-Resident Graph Indexing for High-Throughput Vector Search

Graph-based approximate nearest neighbor search (ANNS) methods (e.g., HNSW) have become the de facto state of the art for their high precision and low latency. To scale beyond main memory, recent out-of-memory ANNS systems leverage SSDs to store large vector indexes. However, they still suffer from severe CPU underutilization and read amplification (i.e., storage stalls) caused by limited access locality during graph traversal. We present VeloANN, which mitigates storage stalls through a locality-aware data layout and a coroutine-based asynchronous runtime. VeloANN utilizes hierarchical compression and affinity-based data placement scheme to co-locate related vectors within the same page, effectively reducing fragmentation and over-fetching. We further design a record-level buffer pool, where each record groups the neighbors of a vector; by persistently retaining hot records in memory, it eliminates excessive page swapping under constrained memory budgets. To minimize CPU scheduling overheads during disk I/O interruptions, VeloANN employs a coroutine-based asynchronous runtime for lightweight task scheduling. On top of this, it incorporates asynchronous prefetching and a beam-aware search strategy to prioritize cached data, ultimately improving overall search efficiency. Extensive experiments show that VeloANN outperforms state-of-the-art disk-based ANN systems by up to 5.8x in throughput and 3.25x in latency reduction, while achieving 0.92x the throughput of in-memory systems using only 10% of their memory footprint.

cs.DB↗

arXiv2026

A classification of regular maps with Euler characteristic $-pq$

In this paper, we give a classification of regular maps with Euler characteristic $-pq$ for distinct primes $q>p\geq 5$. This together with previous classification of regular maps with Euler characteristic $-2p,-3p$ and $-p^2$ completes the classification of regular maps with Euler characteristic $-pq$ for two primes $p$ and $q$. An interesting consequence is that, for every pair of twin primes $p$ and $q$ greater than $5$, there exist three regular maps with solvable automorphism groups and Euler characteristic $-pq$, up to duality and isomorphism.

math.GR↗

arXiv2026

A classification of regular maps with Euler characteristic $-p^4$ for a prime $p\geq 5$

A map is a cellular decomposition of a closed surface. In the framework of classifying all regular maps by their supporting surface, it is an open problem to find all closed surfaces that support no regular maps. Classification of regular maps on surfaces with Euler characteristic $-p, -p^2, -p^3, -2p,$ and $-3p$ has already been done by several authors in a series of papers, which also show that surfaces with these Euler characteristic support no regular maps if the corresponding prime $p$ satisfies certain conditions. In this paper, assuming that $p\geq 5$ is a prime and $i\geq 4$, we show that the order of a Sylow $p$-subgroup of a regular map with Euler characteristic $-p^i$ is bounded by $p^{i-1}$ unless $p\in \{5, 7, 13\}$, and we show the existence of a normal $p$-subgroup for these regular maps whenever a Sylow $p$-subgroup has order at least $\sqrt{p^i}$, laying a solid foundation for using an inductive method to completely characterize regular maps of Euler characteristic $-p^i$. Based on this, we classify all regular maps with Euler characteristic $-p^4$ for a prime $p\geq 5$ in terms of reduced presentations of their automorphism groups. Consequently, a closed surface with Euler characteristic $-p^4$ supports no regular maps if and only if $p\notin \{2,3,5,7,13\}$.

math.GR↗

arXiv2025

Low Rank Learning for Offline Query Optimization

Recent deployments of learned query optimizers use expensive neural networks and ad-hoc search policies. To address these issues, we introduce \textsc{LimeQO}, a framework for offline query optimization leveraging low-rank learning to efficiently explore alternative query plans with minimal resource usage. By modeling the workload as a partially observed, low-rank matrix, we predict unobserved query plan latencies using purely linear methods, significantly reducing computational overhead compared to neural networks. We formalize offline exploration as an active learning problem, and present simple heuristics that reduces a 3-hour workload to 1.5 hours after just 1.5 hours of exploration. Additionally, we propose a transductive Tree Convolutional Neural Network (TCNN) that, despite higher computational costs, achieves the same workload reduction with only 0.5 hours of exploration. Unlike previous approaches that place expensive neural networks directly in the query processing ``hot'' path, our approach offers a low-overhead solution and a no-regressions guarantee, all without making assumptions about the underlying DBMS. The code is available in \href{https://github.com/zixy17/LimeQO}{https://github.com/zixy17/LimeQO}.

cs.DB↗

arXiv2025

Multimodal Large Models Are Effective Action Anticipators

The task of long-term action anticipation demands solutions that can effectively model temporal dynamics over extended periods while deeply understanding the inherent semantics of actions. Traditional approaches, which primarily rely on recurrent units or Transformer layers to capture long-term dependencies, often fall short in addressing these challenges. Large Language Models (LLMs), with their robust sequential modeling capabilities and extensive commonsense knowledge, present new opportunities for long-term action anticipation. In this work, we introduce the ActionLLM framework, a novel approach that treats video sequences as successive tokens, leveraging LLMs to anticipate future actions. Our baseline model simplifies the LLM architecture by setting future tokens, incorporating an action tuning module, and reducing the textual decoder layer to a linear layer, enabling straightforward action prediction without the need for complex instructions or redundant descriptions. To further harness the commonsense reasoning of LLMs, we predict action categories for observed frames and use sequential textual clues to guide semantic understanding. In addition, we introduce a Cross-Modality Interaction Block, designed to explore the specificity within each modality and capture interactions between vision and textual modalities, thereby enhancing multimodal tuning. Extensive experiments on benchmark datasets demonstrate the superiority of the proposed ActionLLM framework, encouraging a promising direction to explore LLMs in the context of action anticipation. Code is available at https://github.com/2tianyao1/ActionLLM.git.

cs.CV↗

arXiv2024

LHPF: Look back the History and Plan for the Future in Autonomous Driving

Decision-making and planning in autonomous driving critically reflect the safety of the system, making effective planning imperative. Current imitation learning-based planning algorithms often merge historical trajectories with present observations to predict future candidate paths. However, these algorithms typically assess the current and historical plans independently, leading to discontinuities in driving intentions and an accumulation of errors with each step in a discontinuous plan. To tackle this challenge, this paper introduces LHPF, an imitation learning planner that integrates historical planning information. Our approach employs a historical intention aggregation module that pools historical planning intentions, which are then combined with a spatial query vector to decode the final planning trajectory. Furthermore, we incorporate a comfort auxiliary task to enhance the human-like quality of the driving behavior. Extensive experiments using both real-world and synthetic data demonstrate that LHPF not only surpasses existing advanced learning-based planners in planning performance but also marks the first instance of a purely learning-based planner outperforming the expert. Additionally, the application of the historical intention aggregation module across various backbones highlights the considerable potential of the proposed method. The code will be made publicly available.

cs.RO↗