arXiv subjects

Can Xu

Publications and source records attributed to Can Xu.

At least 19 recordsLinked to original sources

arXiv2026

EMBER: A Little Red Dot Candidate at $z_{\rm spec}=10.36$ in the Seed Black Hole Era

Little red dots (LRDs) are a newly discovered population that may trace rapidly growing black holes (BHs) and provide a link between seed BHs and luminous active galactic nuclei (AGNs). However, no LRD had previously been spectroscopically confirmed at $z>10$, leaving this earliest phase observationally unexplored. Using JWST/NIRSpec spectroscopy from the EMBER program, we measure a spectroscopic redshift of $z_{\rm spec}=10.361^{+0.003}_{-0.002}$ for \target, the highest-redshift LRD candidate known to date. The redshift is constrained by a prominent Ly$α$ break and multiple tentative emission lines, including C\,{\sc iv}\,$λ\lambda1549,1551$ and [O\,{\sc iii}]\,$\lambda4363$ detected at $S/N=3.9$ and $3.6$, respectively. Its extreme NIRCam-MIRI color of $m_{\rm F444W}-m_{\rm F770W}=1.82\pm0.1$, characteristic V-shaped continuum with a turnover near the Balmer limit, and continuum slopes of $β_{\rm UV}=-2.26^{+0.11}_{-0.11}$ and $β_{\rm opt}=1.17^{+0.74}_{-0.70}$ all support its LRD nature. A possible iron complex at $λ_{\rm rest}\sim0.24$--$0.25\,{\rm μm}$ and a possibly high $\log\left([{\rm O\,III]\,\lambda4363/\rm Hγ}\right)=0.17^{+0.24}_{-0.22}$ further support an AGN-like interpretation, as seen in previously known LRDs. Tentative detection of Ly$α$ emission may indicate enhanced Ly$α$ transmission at $z\sim10$. Our findings extend the observational frontier of BH growth into the seed-BH formation era, and upcoming MIRI spectroscopy will further establish the physical nature of the source.

astro-ph.GA↗

arXiv2026

The Structural Anatomy of Galaxies: Environmental Dependence of Morphological and Quenching Evolution at 0.1 < z < 0.5

We investigate how cluster environments affect galaxy star formation, structure, and stellar populations using spectroscopically-confirmed galaxies in X-ray-selected eROSITA clusters, that have deep HSC-SSP imaging and DESI DR1 spectroscopy. At 0.1<z<0.5, we compare dust-corrected Ha star formation rates (SFRs), effective radii (Re), bulge-to-total light ratios (B/T), and Dn4000 between cluster satellites and a stellar-mass- and redshift-matched field control sample. We identify UVJ-quiescent galaxies and divide the UVJ star-forming population at log(sSFR_Ha)= -10.5 yr-1 into actively star-forming and Ha-low systems, the latter referred to as green-valley (GV) galaxies. Cluster--field differences depend strongly on stellar mass, projected cluster-centric radius, and galaxy population. Cluster star-forming galaxies show modest SFR suppression but weak structural offsets. The strongest coupled signatures occur among Ha-low UVJ-star-forming galaxies, particularly low-mass satellites at R<0.5R500, which have lower SFRs, smaller light-weighted sizes, larger B/T, and larger Dn4000 than matched field counterparts. Quiescent galaxies show weaker structural offsets but retain a positive Dn4000 residual. We quantify the joint signal using a Mahalanobis distance based on matched residuals in SFR, Re, B/T, and Dn4000 with a field--field reference covariance. The multivariate offset is largest for low-mass GV galaxies and decreases toward larger projected radius. The broader radial extent of SFR suppression relative to structural offsets suggests that star-formation suppression has a broader environmental reach than structural transformation. These results show that environmental quenching and structural transformation are most strongly coupled in the Ha-low transition population.

astro-ph.GA↗

arXiv2026

Negative Advantages Is a Double-Edged Sword: Calibrating advantages in GRPO for Search Agents

Search agents achieve strong question-answering performance through multi-turn interactions with search engines, with Group Relative Policy Optimization (GRPO) being a widely used training algorithm. However, GRPO-style algorithms still face several challenges in multi-hop search settings. First, correct intermediate steps are often penalized when the final answer is wrong. Second, training is highly unstable, often causing degradation of natural language ability or even catastrophic training collapse. Our analysis attributes these issues to coarse-grained advantage assignment and an imbalance between positive and negative advantages. To address these problems, we propose CalibAdv, an advantage calibration method specifically designed for search agents that enables more accurate and more stable modeling of penalties and rewards. Specifically, CalibAdv leverages the correctness of intermediate steps to downscale excessive negative advantages at a fine-grained level. It then further rebalances positive and negative advantages to improve training stability. Importantly, CalibAdv adopts a lightweight design that calibrates advantages from standard rollout signals, making it simple and easy to deploy. Extensive experiments across three models and seven benchmarks demonstrate that CalibAdv improves both model performance and training stability. Our code is available at https://github.com/wujwyi/CalibAdv.

cs.CL↗

arXiv2026

FOCUS: Fine-Grained Open-Vocabulary Change Detection for Uncertainty-Aware Semi-Static Scenes

Autonomous robots operating over long periods must keep their environmental memory up to date as the world changes between visits. In semi-static environments, an object may be replaced in place by a different but geometrically and semantically similar instance, making the identity change difficult to detect from geometry or coarse semantics alone. We present FOCUS, an uncertainty-aware framework for object-level change detection and map maintenance. We formulate semi-static memory maintenance as probabilistic inference that fuses geometric likelihood with appearance likelihood rendered from a 3D Gaussian map. A recursive three-state estimator maintains whether each mapped object is PERSISTED, REPLACED, or REMOVED. To account for imperfect 3DGS rendering, we model the rendered appearance evidence probabilistically rather than using it as a direct change score, with the model parameters automatically calibrated from a change-free replay of the initial mapping session. We evaluate our method on a new Isaac Sim warehouse benchmark with ambiguous in-place replacements and on the real-world TorWIC dataset. It improves object-level replacement F1 from 0.20 to 0.84 over a probabilistic baseline and transfers to real-world data without manual parameter retuning.

cs.RO↗

arXiv2026

TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training

On-policy distillation (OPD) trains a student policy by matching a stronger teacher on the student's own trajectories, offering a promising framework for language agent training. However, its application to long-horizon agentic tasks remains insufficiently explored. We identify two key inefficiencies in vanilla agent OPD: (1) full-horizon rollouts often waste wall-clock resources on tail turns that provide weak and noisy KL supervision, and (2) trajectory-level KL objectives concentrate most of the loss on shallow tokens, leaving deeper decision turns under-trained once initial behaviors are aligned. To address these challenges, we propose TurnOPD, a turn-level budgeting strategy for efficient on-policy distillation of long-horizon agents. TurnOPD consists of two budget controllers: adaptive rollout-depth budgeting, which uses probe-based turn statistics to determine rollout length, and progressive turn-normalized loss budgeting, which gradually shifts KL weighting from token-level to turn-balanced supervision. Experiments on ALFWorld, WebShop, and Multi-Hop Search with task-specialized teacher models show that TurnOPD achieves superior validation accuracy under equal wall-clock training budgets and advances the accuracy--time frontier beyond vanilla OPD.

cs.AI↗

arXiv2026

CHAMPS: The COSMOS High-Redshift ALMA-MIRI Population Survey - A New Census of the Dusty Early Universe

Understanding how dust forms and evolves over cosmic time is a key open problem in extragalactic astrophysics. Galaxies in the early Universe were once thought to be mostly dust-poor, but recent discoveries of heavily dust-obscured galaxies near the Epoch of Reionization challenge models of early dust production and raise new questions about the true cosmic star formation rate density. In this paper, we present the COSMOS High-Redshift ALMA-MIRI Population Survey (CHAMPS), which sheds light on the dusty early universe at z>4. CHAMPS is a new 144h ALMA 1.2mm (band 6) large program mapping the combined JWST/NIRCam+MIRI footprint in the COSMOS field. It covers 0.2deg2 with a synthesized beam size of 1.1" and a sensitivity of 0.14mJy/beam. It is complemented, alongside JWST, by ancillary X-ray, UV, optical, sub-mm, and radio data. CHAMPS, optimized as a blind survey, detects above 5$σ$ approximately 385 individual dusty high-redshift sub-mm sources, 68 dusty AGN, and a dozen dusty galaxies at z>6. The galaxies are largely not detected in JWST/F150W, making them prototypical near-IR dark galaxies. We showcase three of the highest-redshift most dusty and massive candidate galaxies detected in CHAMPS with redshifts up to z=7.5. CHAMPS also enables stacks of thousands of galaxies grouped in bins of various physical parameters. Its sub-mm coverage of dust-attenuated JWST-identified galaxies provides robust constraints on dust masses and obscured star formation rates to study early dust formation and evolution. In addition, CHAMPS enables a blind search for luminous CO line emitters at z=0.4-2.7 and [CII]158$μ$m emitters at z=6.7.

astro-ph.GA↗

arXiv2026

CHAMPS: Data Reduction and Detection of ~3300 Dusty Galaxies at 1.2 mm

We present the reduction and source catalogs for the \textit{COSMOS High-$z$ ALMA-MIRI Population Survey} (CHAMPS), the largest Atacama Large (Sub)Millimeter Array (ALMA) blank field survey to date at 0.2\,deg$^2$. With observing frequency centered at $250\, $GHz ($1.2\,$mm) and bandwidth of 7.5 GHz, CHAMPS covers the JWST/NIRCam+MIRI footprint in the COSMOS field, taking advantage of the rich, multiwavelength ancillary datasets in COSMOS ranging from X-ray to radio. The majority of the CHAMPS survey (90$\%$) has depths at or below 200 $μ$Jy beam$^{-1}$ and with an average RMS of 146 $μ$Jy beam$^{-1}$. The reduced CHAMPS mosaic has a beam size of $θ_{\rm res} = 1.1'' \times 1.1''$. CHAMPS identifies sources via two detection methods, a blind search for high-SNR sources, and a prior-based search involving MIRI detections to identify faint sources. The blind search yields a total of 595 sources down to an SNR $\ge4.5σ$ while the prior catalog yields a total of 3162 source down to an SNR $\ge3σ$, leading to a full sample of 3355 unique objects detected across both catalogs. We identify a unique population of 385 SNR $\ge5σ$ sources across the two catalogs; after excluding 9 likely spurious edge detections we define a robust science sample of 376 sources above $\ge5σ$. These sources have a median redshift of $\langle z_{1.2 \text{ mm}}\rangle = 2.54^{+0.89}_{-1.69}$ based on optical/near-IR/mid-IR photometric redshifts and high-quality spectroscopic redshifts, and hold a median stellar mass of $\langle\log (\rm M_\star/M_\odot)\rangle = 10.79^{+0.42}_{-3.08}$. We have further identified 68/376 ($\sim18\%$) sources as candidate AGN through X-ray, UV-optical, infrared and radio selection techniques.

astro-ph.GA↗

arXiv2026

Hunyuan-A13B Technical Report

We present Hunyuan-A13B, an open-source large language model based on a Mixture-of-Experts architecture. It contains 80 billion total parameters but activates only 13 billion during inference, balancing model capability, computational efficiency, and deployment cost. The model is pretrained on a rigorously filtered 20T-token corpus with enhanced STEM data curation, improving factual reliability and reasoning ability. High-quality supervised fine-tuning and large-scale reinforcement learning further enhance its overall performance. Hunyuan-A13B also introduces a dual-mode Chain-of-Thought framework that adapts reasoning depth to task complexity: fast thinking for routine queries and slow thinking for complex, multi-step problems. Evaluations show competitive performance across mathematics, science, programming, general language understanding, and agent tasks, often approaching that of much larger models. Its high inference throughput makes it suitable for latency-sensitive applications. We release Hunyuan-A13B to support open research and practical LLM deployment.

cs.AI↗

arXiv2026

From Transient Prompts to Persistent Control: Scientific Poster Generation via Recursive Semantic-Geometric Contracts

Scientific poster generation distills a multimodal paper into a single-page visual artifact, forcing strict trade-offs between informational coverage and readability under a fixed spatial budget. Existing methods pass plans as transient prompts and validate individual stages in isolation. This strategy causes requirements to drift across content and layout modules, and previous checks to be silently invalidated. We introduce PosterVisor, a control framework that shifts poster generation from transient prompts to persistent control. An Orchestrator grounds rubrics in the paper and visual assets, compiling them into a Semantic-Geometric Contract (SGC) that binds claims and sources to required visuals, budgets, and spatial commitments. Only fully instantiated records become executable assertions; other usable requirements remain soft guidance. Recursive Contract Enforcement (RCE) dynamically triggers checks across stages as evidence emerges. Crucially, during repairs, RCE rechecks affected checkpoint states, preventing repair-induced regressions from propagating silently. We instantiate PosterVisor in HTML/CSS and editable PPTX generators. On the 100-paper Paper2Poster benchmark, PosterVisor-PPT improves observed mean poster-grounded QA accuracy over PosterGen (64.47% vs. 58.53%) and is preferred by human judges in 72.5% of non-tied pairwise comparisons (95% CI, 61.6-83.4%). A secondary 30-paper study also yields higher VLM Overall and PaperQuiz means. These results support rubric-compiled contracts and stage-conditioned enforcement for controllable poster synthesis.

cs.AI↗

arXiv2026

MAC-I$^2$: Learned Metrics-Aware Covariance for Robust Visual-Inertial Fusion in Initialization and Calibration

Visual-Inertial (VI) fusion is fundamental to accurate and robust state estimation, where camera and IMU measurements are combined according to their respective uncertainties. Existing methods, however, fuse the two modalities with predefined uncertainties, regardless of how reliable each is in the local context, and thus often struggle under challenging environments involving illumination changes, dynamic objects, and textureless regions. In this paper, we present MAC-I$^2$, which achieves robust VI fusion through learned metric-aware covariance for both modalities, so that vision and IMU compete on their own merits rather than relying on predefined uncertainties. Here, metrics-aware means that each predicted covariance faithfully reflects the actual magnitude of the corresponding measurement noise. On the visual side, we propagate learned feature-matching uncertainties into pose covariances for the fusion. On the inertial side, motivated by the observation that integration error accumulates sharply at the early stage and grows slowly afterward, we design a learned IMU model with a learnable initial covariance, and propose a dedicated fine-tuning strategy on a held-out training subset to enable the metrics-aware covariance on unseen sequences. As a showcase, we build a VI initialization and calibration system, since accurate and robust initialization and calibration are the prerequisite for any reliable VI system. Experiments on EuRoC, and VBR show that MAC-I$^2$ substantially outperforms existing methods: it achieves a 99.9% initialization success rate on EuRoC, reducing gravity and velocity errors by about 60% and 42% over the strongest baseline, and maintains 80% success rate on challenging VBR sequences where baseline methods such as VINS-Mono drop below 10%.

cs.RO↗

arXiv2026

DuMateBench: Evaluating Autonomous Agents in Complex Real-World Workflows

Autonomous agents are increasingly adopted to complete complex, multi-tool workflows in real-world settings. However, existing benchmarks typically separate tasks by application or capability and evaluate agents in environments that are cleaner and more stable than those encountered in practice. We introduce DuMateBench, a real-session benchmark reconstructed from anonymized and privacy-screened user sessions collected from a large-scale production agent platform. Each task preserves the relevant pre-solution interaction history, persistent configurations, and workspace state, and is then validated through human verification. The resulting benchmark comprises 200 tasks spanning 8 broad scenarios and 17 fine-grained capability categories, with most tasks requiring multiple capability coordination. We execute these tasks in isolated Docker containers injected with three forms of real-world environmental complexity: Insufficient, Unstable, and Noisy, and assess performance using a hybrid deterministic and LLM-as-Judge evaluation protocol. Experiments across five representative autonomous-agent frameworks paired with four state-of-the-art LLMs reveal substantial gaps in strict task completion. Complementary robustness, efficiency, and diagnostic analyses further show that performance under environmental perturbations is jointly shaped by the capabilities of the LLM and the surrounding agent framework. The code and data are publicly available at https://dumatebench.com/.

cs.AI↗

arXiv2026

Dust in the Average Galaxy: Attenuation, Emission, and Opacity from $0<z<7$

We present constraints on the dust emission and attenuation properties of galaxies across 0 10^{10.5}M_\odot$. We derive empirical relationships for the effective attenuation, dust temperature, fraction of star formation that is unobscured, and dust-to-stellar mass ratio as functions of redshift and stellar mass. We separate the first order effect of star/dust geometry from dust grain properties by combining constraints on the IR SED, UV SED, and dust mass surface density. Importantly, we measure over an order of magnitude decrease in $κ_{UV}/κ_{FIR}$--the ratio of dust mass absorption coefficients in the UV at 1600Å and FIR at 500$μ$m--from z~0 to z~7. A depressed $κ_{UV}/κ_{FIR}$ is consistent with a deficit of small dust grains, possibly attributable to the intense radiation fields of high-$z$ star formation; indeed, we find a redshift-invariant inverse relationship between $κ_{UV}/κ_{FIR}$ and $Σ_{SFR}$. Most evolution in the dust-to-stellar ratio is at $z<1$, the product of mild downward evolution in the dust-to-gas ratio combined with steep evolution in the gas-to-stellar ratio. The significant evolution and dynamic range of $κ_{UV}/κ_{FIR}$ and prevailing disconnect between the UV/optical and FIR regimes emphasize that direct dust constraints are irreplaceable for the majority of star-forming galaxies at z<7, not just the most extreme star-formers.

astro-ph.GA↗

arXiv2026

PNEC-Mamba: Prototype-Guided Positive-Negative Evidence Calibration for Hyperspectral Image Classification

In real-world hyperspectral scenes, pixel representations are often ambiguous due to factors such as spectral similarity, mixed pixels, and local context interference, which may simultaneously encode discriminative evidence and interfering information. Existing methods mainly focus on learning more powerful representations or modeling broader contexts, but rarely investigate whether the learned representations provide reliable evidence or introduce interference into classification decisions. To address this issue, we view hyperspectral image classification from the perspective of pixel-level evidence reliability modeling and propose PNEC-Mamba, a prototype-guided positive-negative evidence calibration framework. The framework progressively establishes semantic references, separates class-related evidence from interference, estimates pixel-level reliability, and performs selective calibration. First, a full-image state-space encoder extracts pixel representations, while dynamic class prototypes provide semantic references that evolve jointly with the feature space. Subsequently, positive and negative evidence is derived from pixel-prototype competition, explicitly separating discriminative cues that support classification from confusing signals associated with competing classes. Based on these evidence relationships, a multi-source uncertainty estimation strategy is introduced to assess pixel-level reliability, enabling stronger evidence calibration for uncertain regions. Finally, a full-resolution consistency refinement step is applied to recover local spatial details and improve boundary coherence in the final predictions. Extensive experiments on three benchmark datasets demonstrate that PNEC-Mamba achieves superior classification performance compared with state-of-the-art methods.

cs.CV↗

arXiv2026

From Starburst to Quenching: Physical Properties of Extremely Compact Starbursts at z$\sim$0.1

The compaction phase plays a crucial role in galaxy evolution, as it is strongly linked to star formation activities and structural transformation. We have identified a sample of extremely compact starburst galaxies (eCSBs) at low redshift~(z$\sim$0.1), which represent this critical evolutionary stage. These eCSBs are massive outliers with intense star formation and high infrared luminosities comparable to (U)LIRGs, while their structure already resembles quiescent galaxies. To investigate their molecular gas properties, we conducted IRAM 30m observations of $^{12}$CO J = 1--0 and $^{12}$CO J = 2--1 emission lines. Our results indicate that eCSBs exhibit a notably low molecular gas fraction~($\sim3\%$), and short gas depletion time~($\sim$ 20 Myr), suggesting that these galaxies are rapidly exhausting their remaining gas reservoir. Compared to normal (U)LIRGs, eCSBs show systematically lower $^{12}$CO(2-1)/$^{12}$CO(1-0) ratio~($R_{21} \sim 0.65 \pm 0.06$), similar to main sequence galaxies. The relatively low CO excitation may be associated with their high central stellar mass densities. These findings provide new insight into the molecular gas properties of galaxies during the compaction phase, highlighting their unique condition and rapid evolution toward quiescence.

astro-ph.GA↗

arXiv2026

Playing 20 Question Game with Policy-Based Reinforcement Learning

The 20 Questions (Q20) game is a well known game which encourages deductive reasoning and creativity. In the game, the answerer first thinks of an object such as a famous person or a kind of animal. Then the questioner tries to guess the object by asking 20 questions. In a Q20 game system, the user is considered as the answerer while the system itself acts as the questioner which requires a good strategy of question selection to figure out the correct object and win the game. However, the optimal policy of question selection is hard to be derived due to the complexity and volatility of the game environment. In this paper, we propose a novel policy-based Reinforcement Learning (RL) method, which enables the questioner agent to learn the optimal policy of question selection through continuous interactions with users. To facilitate training, we also propose to use a reward network to estimate the more informative reward. Compared to previous methods, our RL method is robust to noisy answers and does not rely on the Knowledge Base of objects. Experimental results show that our RL method clearly outperforms an entropy-based engineering system and has competitive performance in a noisy-free simulation environment.

cs.HC↗

arXiv2026

VeriEvol: Scaling Multimodal Mathematical Reasoning via Verifiable Evol-Instruct

Scaling reinforcement learning for visual mathematical reasoning requires more than generating harder questions: as data volume grows, the reward labels themselves must remain reliable. Yet existing data pipelines scale supervision while trusting the labeller, and policy-side methods assume the underlying answers are already correct. We instead treat scaling as a verifiable data-construction problem and decouple two axes before any policy update: prompt difficulty, expanded by route-specific evolution operators, and answer reliability, enforced by offline hypothesis-test falsification. We instantiate this as VeriEvol, an iterative framework with two extensible components: a type-aware evolution module that rewrites low-difficulty image-question seeds into harder, image-grounded prompts; and HTV-Agent, a verifier that accepts an answer only after multi-source counter-evidence has failed to refute it. The resulting verified data scales in volume, extends by adding evolution routes or verifier channels, and plugs directly into existing GRPO-style RL recipes. On a five-benchmark visual-math suite, scaling evolved SFT data from 10K to 250K samples raises the mean accuracy from 35.42 to 54.73; then, with backbone, SFT initialization, and GRPO recipe held fixed, VeriEvol adds a cumulative +3.88 over an un-evolved RL baseline, of which +1.82 comes from evolved prompts and +2.06 from the HTV-Agent verifier. We release the prompts, data, models, code, and the full verifier trace of every sample, so that downstream work can scale and audit the pipeline rather than only inspect its outputs.

cs.AI↗

arXiv2026

Ram-pressure stripping caught in action in a young cluster at $z = 2.51$

Galaxy clusters in the local Universe are dominated by massive quiescent galaxies with old ages, formed at high redshifts. Whether their quenching is driven by internal processes or environmental effects is a matter of debate that has been challenging to resolve due to the lack of observations during their peak formation epoch. Here we report clear evidence from the Atacama Large Millimeter/submillimeter Array of extended and elongated gas tails in five galaxies in a forming cluster at z = 2.51. The single-tailed gas distributions, which extend notably beyond the stellar emission probed by JWST in galaxies that are relatively isolated and lack signatures of mergers or interactions (features that are very uncommon in the field), provide evidence of ram-pressure stripping. These very distant confirmed cases of ram-pressure stripping highlight the critical role of environmental effects in gas removal at high redshifts, an often-overlooked quenching pathway.

astro-ph.GA↗

arXiv2026

STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability

Reinforcement Learning with Verifiable Rewards algorithms like GRPO have emerged as the dominant post-training paradigm for complex reasoning in LLMs, yet commonly suffer from policy entropy collapse during training. We conduct a first-order gradient analysis of token-level entropy dynamics under GRPO and identify a token-level credit assignment mismatch: the per-token entropy variation decomposes into the product of the trajectory-level advantage and an entropy sensitivity function over the next-token distribution, yielding an advantage-surprisal four-quadrant structure and a near-criticality property. Motivated by it, we propose STARE (Surprisal-guided Token-level Advantage Reweighting for policy Entropy stability), which identifies entropy-critical token subsets via batch-internal surprisal quantiles, selectively reweights their effective advantages, and incorporates a target-entropy closed-loop gate for stable entropy regulation. Across model scales from 1.5B to 32B and three task families (Short CoT, Long CoT, and Multi-Turn Tool Use), STARE sustains stable RL training over thousands of steps while maintaining policy entropy within the target band. On AIME24 and AIME25, STARE outperforms DAPO and other competitive baselines by 4%-8% in average accuracy, with reflection tokens and response length growing in tandem, indicating sustained exploration-exploitation balance that further unlocks RL training potential.Code is available at https://github.com/hp-luo/STARE.

cs.LG↗