arXiv subjects

Gang Fang

Publications and source records attributed to Gang Fang.

10 recordsLinked to original sources

arXiv2026

DualMem: Bypassing the Objectness Bottleneck for Calibrated Unknown-Stream Filtering in Open-World Object Detection

Open-world object detection (OWOD) requires detectors to localize known classes while identifying unknown objects for future incremental learning. We find that the unknown prediction streams of strong OWOD detectors are heavily polluted: on M-OWODB, across PROB, OW-DETR, and HypOW, future-task positive unknowns make up less than 10% of unknown predictions, whereas background false positives account for 46-71%. We show that this is not a missing-information problem, but an information bottleneck at the objectness head. On PROB Task 1, a linear probe on the 256-D decoder query achieves an AUROC of 0.908 for positive-versus-negative unknown discrimination, but the final one-dimensional objectness scalar drops to 0.642. A frozen SigLIP feature, without access to the detector, independently recovers much of this proposal-level separability at the filtering stage (AUROC = 0.871). Motivated by this finding, we propose DualMem, a calibrated post-hoc filter that assumes a small image-disjoint annotated calibration split of held-out future-task objects and performs a non-parametric likelihood ratio test in frozen SigLIP feature space. DualMem uses a k-nearest-neighbor positive memory to protect future-task objects and a negative memory to suppress background-like proposals. Its decision threshold is chosen by Neyman-Pearson calibration, giving users an explicit trade-off between false-unknown suppression and novel recall. Across PROB, OW-DETR, and HypOW on M-OWODB Task 1, DualMem reduces background-type false unknown proposals per image by 44.9%-66.3%, with a mean reduction of 56.6%. On PROB Task 1, it more than doubles the reduction achieved by a natural K-means prototype baseline, while leaving known-class mAP unchanged because known detections bypass the filter.

cs.CV↗

arXiv2026

Evidence-Guided Unknown Rejection for High-Confidence Near-Known Unknowns

Open-set recognition systems face a neglected failure mode: high-confidence near-known unknowns, which lie outside the known label set but are close enough to known classes that a closed-set classifier accepts them with high confidence. We show that this failure is widespread across scalar-threshold methods, including recent post-hoc detectors, and that stronger encoders can amplify rather than remove the risk. We propose EGUR-A, which changes the decision from ``is this sample's score high enough?'' to ``does this predicted known class have sufficient evidence to accept this sample?'' EGUR-A combines class-conditional local acceptance evidence with global residual evidence, and selects their relative weight from known-sample statistics without unknown validation data. Across CUB, FGVC-Aircraft, and ImageNet-hard, EGUR-A substantially reduces high-confidence false known acceptance at matched known-rejection operating points. The result is not a stronger threshold; it is a different question: whether a known class is entitled to accept a sample.

cs.CV↗

arXiv2026

Community-aware evaluation and threshold calibration for open-set plankton image recognition

Automated plankton image recognition is increasingly used in aquatic ecosystem monitoring, but deployed classifiers inevitably encounter unseen taxa and non-target particles. Open-set recognition methods are usually evaluated with sample-level metrics such as AUROC, AUPR, and FPR@95% unknown-recall operating points, whereas ecological monitoring depends on community-level estimates of taxon abundance and diversity. This study examines the mismatch between these objectives using controlled pseudo-communities and three datasets spanning marine zooplankton imaged by ZooScan, marine phytoplankton imaged by IFCB, and freshwater plankton imaged by an in-situ camera. We define Open-Set Community Distortion (OSCD), a Bray-Curtis-style error over known taxa plus an unknown bin, with directional components distinguishing known-taxon overestimation from underestimation. Closed-set classifiers achieved high known-class accuracy, but unknown samples were often absorbed with high confidence and in structured ways. Sample-level OOD metrics were not sufficient to select ecological operating points: for MSP, FPR@95% unknown-recall thresholds produced large test-community OSCD on all three datasets mainly because true known taxa were over-rejected into the unknown bin. Community-aware threshold calibration reduced MSP OSCD relative to fixed 95% known recall on SYKE-ZooScan 2024 and SYKE-IFCB 2022; on ZooLake the fixed-recall baseline was already close to the community-aware threshold, and the best community-level method was a prototype-distance variant rather than MSP. The benefit of community-aware calibration therefore depends on validation-community representativeness and the gap between fixed recall and the community optimum. These results show that open-set plankton recognition should be evaluated as an ecological measurement problem, not only as a sample-level detection task.

cs.CV↗

arXiv2026

Cutscene Agent: An LLM Agent Framework for Automated 3D Cutscene Generation

Cutscenes are carefully choreographed cinematic sequences embedded in video games and interactive media, serving as the primary vehicle for narrative delivery, character development, and emotional engagement. Producing cutscenes is inherently complex: it demands seamless coordination across screenwriting, cinematography, character animation, voice acting, and technical direction, often requiring days to weeks of collaborative effort from multidisciplinary teams to produce minutes of polished content. In this work, we present Cutscene Agent, an LLM agent framework for automated end-to-end cutscene generation. The framework makes three contributions: (1)~a Cutscene Toolkit built on the Model Context Protocol (MCP) that establishes \emph{bidirectional} integration between LLM agents and the game engine -- agents not only invoke engine operations but continuously observe real-time scene state, enabling closed-loop generation of editable engine-native cinematic assets; (2)~a multi-agent system where a director agent orchestrates specialist subagents for animation, cinematography, and sound design, augmented by a visual reasoning feedback loop for perception-driven refinement; and (3)~CutsceneBench, a hierarchical evaluation benchmark for cutscene generation. Unlike typical tool-use benchmarks that evaluate short, isolated function calls, cutscene generation requires long-horizon, multi-step orchestration of dozens of interdependent tool invocations with strict ordering constraints -- a capability dimension that existing benchmarks do not cover. We evaluate a range of LLMs on CutsceneBench and analyze their performance across this challenging task.

cs.GR↗

arXiv2025

Zero-Dimensional Stacking Domains Enable Strong-Ductile Synergy in Additive Manufactured Titanium

Alloying by addition of oxygen interstitials during additive manufacturing provides new routes to strengthen and toughen metals and alloys. The underlying mechanisms by which such interstitial atoms lead to enhanced properties remain, however, unclear, not least due a lack of quantitative atomic-scale models linking microstructure to properties. Here using quasi-3D imaging based on multi-slice electron ptychography, we reveal the importance of a new type of interstitial-character lattice defect, namely zero-dimensional stacking domains (ZDSDs), present in high density in AM-processed oxygen-modulated pure titanium. These ZDSDs promote slip diversity, and support intense work hardening, enabling a three-fold enhancement in both strength and ductility in Ti-0.45O compared to conventional pure Ti. The work demonstrates the potential for using interstitial solutes to enhance mechanical properties in a range of critical engineering alloys.

cond-mat.mtrl-sci↗

arXiv2025

The Total Coloring Conjecture holds for planar graphs without three special subgraphs

The Total Coloring Conjecture (TCC) for planar graphs with a maximum degree of six remains open. Previous studies suggest that TCC is valid for such graphs if they do not contain any subgraph isomorphic to a 4-fan. In this paper, we present an improved conclusion by establishing that TCC holds for planar graphs that are free of three particular substructures, namely the mushroom, the tent, and the cone. This advancement enhances previous findings by demonstrating that TCC is applicable to planar graphs with a maximum degree of six, which can accommodate sparse 4-fans, 5-fans, 5-wheels, and 6-wheels.

math.CO↗

arXiv2018

Unexpectedly high salt accumulation inside carbon nanotubes soaked in very dilute salt solutions

We experimentally demonstrate the formation of salt aggregations with unexpectedly high concentration inside multi-walled carbon nanotubes (CNTs) soaked only in dilute salt solutions and even in solutions containing only traces of salts. This finding suggests the blocking of fluid across CNTs by the salt aggregations when CNTs are soaked in a dilute salt solution with the concentration of seawater or even lower, which may open new avenues for the development of novel CNT-based desalination techniques. The high salt accumulation of CNTs also provides a new CNT-based strategy for the collection/extraction of noble metal salts in solutions containing traces of noble metal salts. Theoretical analyses reveal that this high salt accumulation inside CNTs can be mainly attributed to the strong hydrated cation-pi interactions of hydrated cations and pi electrons in the aromatic rings of CNTs.

cond-mat.mtrl-sci↗

arXiv2011

Characterizing Discriminative Patterns

Discriminative patterns are association patterns that occur with disproportionate frequency in some classes versus others, and have been studied under names such as emerging patterns and contrast sets. Such patterns have demonstrated considerable value for classification and subgroup discovery, but a detailed understanding of the types of interactions among items in a discriminative pattern is lacking. To address this issue, we propose to categorize discriminative patterns according to four types of item interaction: (i) driver-passenger, (ii) coherent, (iii) independent additive and (iv) synergistic beyond independent additive. Either of the last three is of practical importance, with the latter two representing a gain in the discriminative power of a pattern over its subsets. Synergistic patterns are most restrictive, but perhaps the most interesting since they capture a cooperative effect. For domains such as genetic research, differentiating among these types of patterns is critical since each yields very different biological interpretations. For general domains, the characterization provides a novel view of the nature of the discriminative patterns in a dataset, which yields insights beyond those provided by current approaches that focus mostly on pattern-based classification and subgroup discovery. This paper presents a comprehensive discussion that defines these four pattern types and investigates their properties and their relationship to one another. In addition, these ideas are explored for a variety of datasets (ten UCI datasets, one gene expression dataset and two genetic-variation datasets). The results demonstrate the existence, characteristics and statistical significance of the different types of patterns. They also illustrate how pattern characterization can provide novel insights into discriminative pattern mining and the discriminative structure of different datasets.

cs.DB↗

arXiv2011

Integration of Differential Gene-combination Search and Gene Set Enrichment Analysis: A General Approach

Gene Set Enrichment Analysis (GSEA) and its variations aim to discover collections of genes that show moderate but coordinated differences in expression. However, such techniques may be ineffective if many individual genes in a phenotype-related gene set have weak discriminative power. A potential solution is to search for combinations of genes that are highly differentiating even when individual genes are not. Although such techniques have been developed, these approaches have not been used with GSEA to any significant degree because of the large number of potential gene combinations and the heterogeneity of measures that assess the differentiation provided by gene groups of different sizes. To integrate the search for differentiating gene combinations and GSEA, we propose a general framework with two key components: (A) a procedure that reduces the number of scores to be handled by GSEA to the number of genes by summarizing the scores of the gene combinations involving a particular gene in a single score, and (B) a procedure to integrate the heterogeneous scores from combinations of different sizes and from different gene combination measures by mapping the scores to p-values. Experiments on four gene expression data sets demonstrate that the integration of GSEA and gene combination search can enhance the power of traditional GSEA by discovering gene sets that include genes with weak individual differentiation but strong joint discriminative power. Also, gene sets discovered by the integrative framework share several common biological processes and improve the consistency of the results among three lung cancer data sets.

q-bio.GN↗

arXiv2011

Construction and Functional Analysis of Human Genetic Interaction Networks with Genome-wide Association Data

Genetic interaction measures how different genes collectively contribute to a phenotype, and can reveal functional compensation and buffering between pathways under genetic perturbations. Recently, genome-wide screening for genetic interactions has revealed genetic interaction networks that provide novel insights either when analyzed by themselves or when integrated with other functional genomic datasets. For higher eukaryotes such as human, the above reverse-genetics approaches are not straightforward since the phenotypes of interest for higher eukaryotes are difficult to study in a cell based assay. We propose a general framework for constructing and analyzing human genetic interaction networks from genome-wide single nucleotide polymorphism (SNP) data used for case-control studies on complex diseases. Specifically, the approach contains three major steps: (1) estimating SNP-SNP genetic interactions, (2) identifying linkage disequilibrium (LD) blocks and mapping SNP-SNP interactions to block-block interactions, and (3) functional mapping for LD blocks. We performed two sets of functional analyses for each of the six datasets used in the paper, and demonstrated that (i) the constructed genetic interaction networks are supported by functional evidence from independent biological databases, and (ii) the network can be used to discover pairs of compensatory gene modules (between-pathway models) in their joint association with a disease phenotype. The proposed framework should provide novel insights beyond existing approaches that either ignore interactions between SNPs or model different SNP-SNP pairs with genetic interactions separately. Furthermore, our study provides evidence that some of the core properties of genetic interaction networks based on reverse genetics in model organisms like yeast are also present in genetic interactions revealed by natural variation in human populations.

q-bio.MN↗