arXiv subjects

Zihao Huang

Publications and source records attributed to Zihao Huang.

At least 19 recordsLinked to original sources

arXiv2026

A Proof of Füredi's Conjecture

We prove Füredi's conjecture on strong Bollobás $t$-systems. For every nonnegative integer $t$, a family of $m\ge2$ pairs of finite sets $(A_i,B_i)$ satisfying $|A_i\cap B_i|\le t$ and $|A_i\cap B_j|>t$ for all $i\ne j$ satisfies \[ \sum_i\binom{|A_i|+|B_i|-2t}{|A_i|-t}^{-1}\le1. \] We first prove a weighted inequality for subspace pairs satisfying the symmetric cross-intersection condition over any field. It follows from a local inequality for graded exterior ideals, proved by induction with projections and colon ideals.

math.CO↗

arXiv2026

An AFLT-type generalization of the $q$-Baker--Forrester ex-conjecture

The Habsieger--Kadell $q$-Morris constant term identity, which is equivalent to the famous $q$-Selberg integral, has been generalized in numerous ways since the 1980s. Among these, there are two important generalizations: (i) the $q$-Baker--Forrester ex-conjecture, which was conjectured by Baker and Forrester in 1998 and proved by Károlyi, Nagy, Petrov and Volkov in 2015; (ii) the AFLT-type $q$-Morris identity (equivalently, the AFLT-type $q$-Selberg integral), which was obtained by Albion, Rains and Warnaar in 2021, as a $q$-analog of the result of Alba, Fateev, Litvinov and Tarnopolskiy (AFLT). In this paper, by the Gessel--Xin method and the Macdonald polynomials with prescribed symmetry, we unify these two generalizations.

math.CO↗

arXiv2026

Representing and Parsing Korean Constituency Structure at Different Levels of Granularity

Korean constituency parsing raises a representational challenge because the terminal units of a phrase-structure tree do not straightforwardly correspond to simple surface words. Korean eojeols are morphologically complex spacing units, and existing constituency resources differ in how they represent eojeol-internal morphology and non-overt elements. This paper compares three constituency parsing representations derived from the Penn Korean Treebank: Morpheme+XPOS, Eojeol+XPOS, and Eojeol+UPOS. We construct these representations by removing null elements, aligning Penn Korean phrase structure with overt eojeol tokens, preserving Penn Korean phrase labels where possible, and varying the terminal and preterminal layers. We then evaluate canonical non-binary transition-based constituency parsers in top-down, in-order, and bottom-up orders under a shared modeling and evaluation setup. All experiments use gold terminal segmentation and gold preterminal labels and therefore evaluate constituency parsing conditioned on gold morphosyntactic annotation. Eojeol terminals yield shorter transition sequences, but Eojeol+UPOS parsing substantially underperforms the morphologically richer conditions. Eojeol+XPOS narrows this gap, while Morpheme+XPOS gives the strongest results even after its predictions are projected to the eojeol terminal domain. Under these gold-annotation conditions, the results show that fine-grained morphological and XPOS representations provide valuable evidence for the evaluated parsers. This empirical finding concerns the information available for parsing and does not by itself determine the linguistically preferable terminal domain. Independently, linguistic and resource-design considerations motivate eojeol as a stable and interpretable surface domain for phrase-structure annotation, with morpheme-level and XPOS information retained as aligned morphosyntactic evidence.

cs.CL↗

arXiv2026

Non-binary bottom-up constituency parsing without arity actions

Non-binary bottom-up constituency parsing commonly uses arity-specific reductions such as $\textsc{Reduce-}X\#k$, which jointly specify the mother label and number of children. We show that arity need not be a primitive transition parameter. The proposed parser predicts the mother label separately and identifies the ordered child sequence from a delimiter-bounded stack configuration. In every well-formed reducible configuration, the active delimiter, label marker, and intervening completed items uniquely determine the reduction domain and hence its arity. This factorization removes label--arity-specific reduction actions while preserving direct construction of the original non-binary trees. Controlled experiments on PTB and CTB show that the delimiter-guided parser closely tracks an arity-specific baseline while using a substantially smaller action inventory. Its predicted trees retain the gold branching profile without systematic collapse at higher arities. The smaller inventory is obtained at the cost of longer derivations and boundary-sensitive errors involving delimiter insertion, preservation, and consumption.

cs.CL↗

arXiv2026

Covering Hypercube $mB^n$

The Alon--Füredi theorem determines the minimum number of hyperplanes needed to cover every nonzero vertex of the Boolean cube while avoiding the origin. We study hyperplane coverings with multiplicity for the generalized hypercube $mB^n=\{0,1,\ldots,m\}^n$. Our main result is a polynomial multiplicity theorem extending the theorem of Sauermann and Wigderson to $mB^n$, with sharp degree bounds for polynomials having prescribed high-order zeros. We apply this result to obtain lower and upper bounds for hyperplane coverings with multiplicity and determine the exact minimum number of hyperplanes for coverings with multiplicities $k=1,2$. In the special case of the Boolean cube, our constructions improve the upper bound of Clifton and Huang for certain ranges of the parameters.

math.CO↗

arXiv2026

TokenStack: A Heterogeneous HBM-PIM Architecture and Runtime for Efficient LLM Inference

Large language model (LLM) serving is now limited by the key-value (KV) cache. During decode, each new token rereads prior KV state, so attention becomes a bandwidth- and capacity-heavy memory task. HBM-PIM helps by moving attention closer to memory, but current stack organizations still waste resources. In practice, only hot KV blocks benefit from near-memory compute. Weights, activations, and cold KV mainly need dense storage and GPU-visible bandwidth. A uniform HBM-PIM stack makes all layers pay for PIM logic, while a dedicated-PIM design such as AttAcc recovers capacity but shrinks the HBM bandwidth left for GPU-side work. We propose TokenStack, a vertically heterogeneous HBM-PIM architecture for KV-centric LLM serving that leverages HBM4's logic-die substrate. TokenStack separates each stack into dense capacity layers and PIM-enabled compute layers, then uses the logic base die as a stack-local control point that manages cross-layer movement without host-side overhead. The base-die controller handles cross-layer DMA, layered address translation, attention-side gather/broadcast coordination, and inline quantization during migration. On top of this hardware, TokenStack uses topology-aware KV placement, workload-aware eviction, and bounded replication to keep hot KV near PIM compute while moving colder state to dense layers. Using production-derived traces across four models, completed multi-QPS runs show that TokenStack increases geometric-mean token throughput by 1.62x and SLO-compliant serving capacity by 1.70x over AttAcc, and reduces per-token energy by 30-47%.

cs.AR↗

arXiv2026

FARS: A Fully Automated Research System Deployed at Scale

Recent automated research systems show that language-model agents can generate hypotheses, run experiments, and write complete manuscripts, but most evidence still comes from selected examples, human-framed topics, or a few pre-defined research tasks. We present FARS (Fully Automated Research System), a fully automated AI-for-AI research system designed to operate across research topics at scale. FARS autonomously generates and advances projects through ideation, planning, experimentation, and writing, using stage-specific agents coordinated through a shared workspace that records proposals, code, logs, results, and manuscripts. In its first public deployment, FARS produced 166 complete research papers spanning 67 fine-grained AI/ML topics while preserving intermediate artifacts as an auditable corpus rather than a curated set of successes. We evaluate this corpus with 282 structured reviews from volunteer reviewers covering 140 papers, including overall ratings, sub-scores, integrity checks, and LLM-use disclosure. The reviews indicate that FARS can produce review-worthy and occasionally strong AI/ML research artifacts in a large-scale public deployment, while also exposing recurring failure modes in narrow experimental scope, methodological limitations, and integrity issues.

cs.AI↗

arXiv2026

GaussianArt: Unified Modeling of Geometry and Motion for Articulated Objects

Reconstructing articulated objects is essential for building digital twins of interactive environments. However, prior methods typically decouple geometry and motion by first reconstructing object shape in distinct states and then estimating articulation through post-hoc alignment. This separation complicates the reconstruction pipeline and restricts scalability, especially for objects with complex, multi-part articulation. We introduce a unified representation that jointly models geometry and motion using articulated 3D Gaussians. This formulation improves robustness in motion decomposition and supports articulated objects with up to 20 parts, significantly outperforming prior approaches that often struggle beyond 2--3 parts due to brittle initialization. To systematically assess scalability and generalization, we propose MPArt-90, a new benchmark consisting of 90 articulated objects across 20 categories, each with diverse part counts and motion configurations. Extensive experiments show that our method consistently achieves superior accuracy in part-level geometry reconstruction and motion estimation across a broad range of object types. We further demonstrate applicability to downstream tasks such as robotic simulation and human-scene interaction modeling, highlighting the potential of unified articulated representations in scalable physical modeling.

cs.CV↗

arXiv2026

OmniView-Space: Reinforcing Spatial Reasoning via Multi-Perspective Spatial Mapping

Spatial intelligence remains a persistent challenge for Multimodal Large Language Models (MLLMs), as it requires coherent spatial scene representations beyond basic object recognition. Existing methods typically build such representations through textual reasoning or 3D reconstruction. However, they often falter during multi-step reasoning, particularly when required to dynamically re-anchor evidence to the specific camera-, object-, or direction-centric reference frames demanded by complex queries. To address this, we propose OmniView-Space, a framework designed to maintain spatial consistency through multimodal egocentric evidence. Our approach consists of three core components: (1) Multi-Perspective Spatial Mapping (MPSM), which re-anchors reconstructed geometry into a query-aligned visual cognitive map and a textual spatial graph; (2) Tool-Guided Egocentric Reasoning, an interleaved policy trained to actively select the ego anchor required by the query and request the corresponding MPSM evidence; and (3) Cognitive-Map Distillation, which uses MPSM-generated trajectories and ego-frame rewards to train the model to reason with self-generated cognitive maps. Experiments on single- and multi-image spatial reasoning benchmarks show that OmniView-Space achieves state-of-the-art performance. Furthermore, the distilled model maintains this performance while reducing reliance on external geometry pipelines.

cs.CV↗

arXiv2026

Position: Reasoning After Perception Means Reasoning Without Vision

A common belief in multimodal research is that the perceptual weaknesses of vision--language models can be compensated by stronger language reasoning (e.g., chain-of-thought, in-context learning, or external tools). We challenge this assumption. We argue that for a broad class of visual tasks hard to specify in language, failures stem from a structural fatality where the temporal decision of \textit{when} to reason strictly dictates the spatial constraint of \textit{where} reasoning takes place. When visual reasoning is deferred to language generation, current architectures do not merely delay computation; they displace it from the continuous visual representation to a discrete textual space. Consequently, the sequential ``Perception-then-Reasoning'' paradigm degenerates perception into a passive, one-off feature encoding process, rendering it functionally equivalent to ``Reasoning-in-Text-Space'', where task-critical spatial signals are collapsed before reasoning begins. We substantiate this claim with the Turing Eye Test (TET): tasks that must be resolved in \emph{visual space} and are hard to verbalize; results show text-only reasoning cannot remedy these perceptual failures. Our findings suggest rethinking the architectural divide: shifting from reasoning \textit{about} perception to reasoning \textit{within} perception. This facilitates actively reasoning-driven perception that operates directly on pixel-level visual representations, rather than within a collapsed textual space.

cs.CV↗

arXiv2026

Improved Large Language Diffusion Models

Modern large language models are predominantly trained with autoregressive factorization and causal attention. We present \emph{iLLaDA}, an 8B masked diffusion language model trained from scratch with fully bidirectional attention. iLLaDA keeps the masked diffusion objective throughout pre-training and supervised fine-tuning (SFT), scaling pre-training to 12T tokens and fine-tuning on a 25B-token instruction corpus for 12 epochs. We further use variable-length generation for efficiency and introduce confidence-based scoring for multiple-choice evaluation. Compared with LLaDA, iLLaDA improves broadly across general, mathematical, and code benchmarks; for example, iLLaDA-Base improves by 21.6 points on BBH and 14.9 points on ARC-Challenge, while iLLaDA-Instruct improves by 14.5 points on MATH and 16.5 points on HumanEval. Despite its non-autoregressive training, iLLaDA also remains competitive with Qwen2.5 7B on several benchmarks. These results show that fully bidirectional diffusion training from scratch is a competitive path toward strong language models. Model weights and codes: https://github.com/ML-GSAI/LLaDA.

cs.CL↗

arXiv2026

SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks

Spatial reasoning is a foundational capability for multimodal large language models (MLLMs) to perceive and operate within the physical world. However, existing benchmarks predominantly rely on passive evaluation (e.g., static VQA) or simulator-specific pipelines, failing to assess general interactive spatial understanding. We introduce SpatialWorld, a unified benchmark designed specifically for evaluating the interactive spatial understanding of multimodal agents in complex real-world tasks. Integrating eight heterogeneous simulation backends under a shared, simulator-agnostic protocol, SpatialWorld features 760 human-annotated tasks across diverse domains (e.g., household routines, travel, social collaboration). Agents must solve tasks under vision-only partial observability, actively gathering egocentric visual evidence and expressing decisions via a unified, text-based action interface native to MLLMs. For reliable evaluation, each task includes a human-validated initial state, a reference trajectory, and a terminal-state verifier. Evaluating 15 advanced agents reveals that robust spatial task solving remains challenging: the strongest model, GPT-5, achieves an average task success rate (TSR) of only 17.4%, while the leading open-source model, Qwen-3.5, reaches 14.1%. Further analysis exposes a clear mismatch between task success and execution efficiency, alongside substantial domain-specific performance variations. These bottlenecks in active exploration and long-horizon planning position SpatialWorld as a rigorous testbed for future spatial agents.

cs.AI↗

arXiv2026

Chinese Grammatical Error Correction: A Survey

Chinese Grammatical Error Correction (CGEC) is a critical task in Natural Language Processing, addressing the growing demand for automated writing assistance in both second-language (L2) and native (L1) Chinese writing. While L2 learners struggle with mastering complex grammatical structures, L1 users also benefit from CGEC in academic, professional, and formal contexts where writing precision is essential. This survey provides a comprehensive review of CGEC research, covering datasets, annotation schemes, evaluation methodologies, and system advancements. We examine widely used CGEC datasets, highlighting their characteristics, limitations, and the need for improved standardization. We also analyze error annotation frameworks, discussing challenges such as word segmentation ambiguity and the classification of Chinese-specific error types. Furthermore, we review evaluation metrics, focusing on their adaptation from English GEC to Chinese, including character-level scoring and the use of multiple references. In terms of system development, we trace the evolution from rule-based and statistical approaches to neural architectures, including Transformer-based models and the integration of large pre-trained language models. By consolidating existing research and identifying key challenges, this survey provides insights into the current state of CGEC and outlines future directions, including refining annotation standards to address segmentation challenges, and leveraging multilingual approaches to enhance CGEC.

cs.CL↗

arXiv2026

A tree interpretation of arc standard dependency derivation

Arc-standard derivations over projective dependency trees can be interpreted as the incremental construction of lexicalized ordered trees with contiguous yields. Each \textsc{shift}, \textsc{leftarc}, and \textsc{rightarc} transition corresponds to a deterministic tree update, and the resulting ordered tree uniquely determines the dependency arcs introduced by the derivation. We show that this representation is not an arbitrary encoding: a single-headed dependency tree admits such a contiguous ordered representation if and only if it is projective. The proposal is therefore derivational rather than conversion-based, since the ordered object is defined over the transition sequence itself rather than obtained by transforming a completed dependency graph. This gives a tree-theoretic interpretation of arc-standard parsing, in which projective dependency derivations implicitly construct recoverable constituency-style ordered trees. For non-projective inputs, the interpretation can be used through pseudo-projective lifting and inverse decoding. A small implementation study confirms that the mapped derivations are executable in an existing neural transition-based parser.

cs.CL↗

arXiv2026

Refining Word-Based Grammatical Error Annotation for L2 Korean

Korean grammatical error correction (K-GEC) presents a structural mismatch between word-based evaluation and the morpheme-level locus of many learner errors. Postpositions and verbal endings are bound to lexical hosts, but they encode grammatical relations that must be represented in correction and evaluation. This paper refines word-based grammatical error annotation for L2 Korean by addressing three connected problems in existing resources: surface target realization, Korean-specific edit annotation, and single-reference evaluation. We reconstruct target sentences from the National Institute of Korean Language (NIKL) L2 corpus under morphologically constrained realization rules and convert its morpheme-level annotations into word-level \texttt{m2} edits. We then define a Korean ERRANT-style annotation scheme that preserves the MRU core while distinguishing functional morpheme errors, spelling errors, word boundary errors, and word order errors. We also augment the KoLLA corpus with an additional reference correction, yielding a multi-reference evaluation setting for Korean GEC. Empirical validation shows that the refined NIKL targets yield lower perplexity, the converted \texttt{m2} files achieve higher agreement with source-target edit representations, and the refined resources improve KoBART-based correction under the same model setting. Multi-reference KoLLA evaluation further reduces the penalty imposed on valid corrections that diverge from a single reference, especially for neural and prompted GEC systems. These results show that Korean GEC evaluation depends not only on correction models, but also on reference data and edit annotations that reflect Korean morphology, spacing, and correction variability.

cs.CL↗

arXiv2026

A generalization of Kadell's orthogonality ex-conjecture

In 2000, Kadell gave an orthogonality conjecture for a symmetric function generalization of the Zeilberger--Bressoud $q$-Dyson constant term identity. The non-zero part of Kadell's conjecture is a constant term identity indexed by a weak composition $v$. This conjecture was first proved by Károlyi, Lascoux and Warnaar in 2015. They further formulated a closed-form expression for the above constant term when all parts of the composition $v$ are distinct. In 2021, Zhou obtained a recursion for this constant term for an arbitrary composition $v$. In this paper, by categorizing the variables into two parts, we generalize Zhou's result.

math.CO↗

arXiv2026

Discovery of a nonsymmorphic superconductor with spontaneous rotational symmetry breaking and nontrivial zero modes

Topological superconductivity has attracted great interest due to its fundamental significance for realizing Majorana quasiparticles and fault-tolerant quantum computation. Nonsymmorphic superconductors, with symmetry-protected nontrivial electronic structures, offer a promising route to exotic topological superconducting states, yet experimental realizations remain scarce. Here we identify nonsymmorphic compound PtPb4 as a robust platform hosting superconductivity with spontaneous rotational symmetry breaking and nontrivial zero-energy modes. PtPb4 crystallizes in a frustrated Shastry-Sutherland lattice and exhibits nontrivial band topology. By combining in-plane and out-of-plane resistivity measurements, pronounced twofold anisotropy is observed in both the superconducting state and the upper critical field, evidencing spontaneous rotational symmetry breaking. Scanning tunneling microscopy/spectroscopy further reveal twofold-symmetric magnetic vortices, providing direct real-space evidence for the symmetry-broken superconducting state. Notably, a robust zero-energy vortex bound state emerges and persists without spatial splitting over extended distances, consistent with the characteristics expected for Majorana bound state. These findings uncover an exotic superconducting state in PtPb4 and establish a promising platform for exploring topological superconductivity and superconducting quantum devices.

cond-mat.supr-con↗

arXiv2026

Q-DeepSight: Incentivizing Thinking with Images for Image Quality Assessment and Refinement

Image Quality Assessment (IQA) models are increasingly deployed as perceptual critics to guide generative models and image restoration. This role demands not only accurate scores but also actionable, localized feedback. However, current MLLM-based methods adopt a single-look, language-only paradigm, which departs from human evidence-seeking judgment and yields weakly grounded rationales, limiting their reliability for in-the-loop refinement. We propose Q-DeepSight, a think-with-image framework that emulates this human-like process. It performs interleaved Multimodal Chain-of-Thought (iMCoT) with tool-augmented evidence acquisition (e.g., crop-and-zoom) to explicitly determine where quality degrades and why. To train these long iMCoT trajectories via reinforcement learning, we introduce two techniques: Perceptual Curriculum Reward (PCR) to mitigate reward sparsity and Evidence Gradient Filtering (EGF) to improve credit assignment for visually-grounded reasoning. Q-DeepSight achieves state-of-the-art performance across diverse benchmarks, including natural, restored, and AI-generated content. Furthermore, we demonstrate its practical value with Perceptual-in-Generation (PiG), a training-free framework where Q-DeepSight's diagnoses guide iterative image enhancement, effectively closing the loop between assessment and refinement.

cs.CV↗