arXiv subjects

Jianzhe Lin

Publications and source records attributed to Jianzhe Lin.

At least 19 recordsLinked to original sources

arXiv2026

When Good Verifiers Go Bad: Silent Negative Transfer in Verifier-Guided VLM Training

Verifier reliability is not portable across tasks. A verifier-guided self-DPO pipeline with genuine held-out gains on MathVista (+9.6 points on self-training data, +8.0 held out) can be harmful on MMMU. The failure is invisible from the target-task self-training signal: over six learner-verifier configurations, MMMU self-training performance still improves by +3.52 points while held-out performance drops by 1.42 points. We call this silent negative transfer: a verifier validated as useful before can still show signatures of successful self-training after its induced update stops transferring to unseen data. Downstream failure alone cannot diagnose this: poor generalization may mean the verifier induces a wrong learning direction, or that the correct direction itself does not generalize beyond the self-training distribution. We separate these effects via gradient fidelity F, the alignment between verifier-induced and correct training directions, and gradient transferability T, the alignment between correct and held-out directions, giving a conservative Safe-Transfer Margin: positive first-order held-out alignment is certified when arccos(F) + arccos(T) < pi/2. We then introduce Asymmetric Acceptance Gating (AAG), a precision-first filter selecting preference pairs by the verifier's absolute confidence in the response receiving the positive update. On MMMU, AAG raises fidelity from 0.29 to 0.42. In a same-cell analysis, the correct direction stays positively aligned with the held-out direction (T = 0.31), yet raw verification rotates the induced update to negative held-out alignment (-0.13); AAG restores positive alignment (+0.22). Across all six MMMU configurations, AAG beats raw verifier-guided training. Verifier reliability thus means not that it worked before, but that it induces the right update on the task at hand and that this update stays useful beyond the data that generated it.

cs.CR↗

arXiv2026

When LLM Agents Fail to Read the Room: ReAdapt for Relational Social Reasoning

A social agent's most basic decisions (should I react to this post? who should I reach out to?) are not purely content problems. The right action often hinges on the latent relationship between people -- tie strength, reciprocity, mutual connections -- rather than on which content is most salient. Standard LLM agent loops do not explicitly represent how new relational evidence should revise the agent's current social hypothesis, leaving them prone to surface-obvious choices when relational and content cues diverge. We formalize this failure mode with a relationship-reasoning benchmark: 500 synthetic social worlds with friendships, follows, reaction histories, and feeds, yielding 1,000 queries over two tasks, reaction selection and warm introduction (finding the best bridge to a target person). By construction, the surface-obvious candidate differs from the relationship-grounded oracle in about 53% of queries, forming an overturn subset where the agent must use relational evidence to revise an initially plausible choice. We propose ReAdapt (Relationship-Adaptive Agent with Policy-driven sTate), which augments the ReAct loop with an explicit structured social state z = (G, B, R, N, D) capturing goal, belief, relationship, norm, and disclosure. After each tool observation, ReAdapt runs a typed Adapt step that updates this state and emits a policy operation (continue, switch, abandon, or clarify) before choosing the next action. With Gemini-3-Flash on a stratified subset of n = 150 queries per task, ReAdapt improves warm-introduction accuracy from 37% to 51% (+14 points) and reaction-selection accuracy from 69% to 77% (+8 points). Oracle regret drops from 0.260 to 0.152 and from 0.095 to 0.053, respectively. Holding the model, tools, and environments fixed, these results suggest that explicit relational-state adaptation helps LLM agents turn retrieved social evidence into revised decisions.

cs.AI↗

arXiv2026

Clarification Is Not Correction: LLMs Fail to Let Go

Dialogue failures in language models are usually framed as memory failures: context too long, summaries lossy, a constraint forgotten. We argue this misses a deeper problem: in many conversations the model does not forget, it commits too early. An ambiguous early turn collapses into a single hidden interpretation, and later clarification is filtered through that commitment. We call this early posterior collapse: unresolved user intent collapsing into a committed task state before ambiguity is resolved. We study it with controlled dialogue tasks in writing, planning, and coding using Gemini-2.5-Pro and Gemini-2.5-Flash. Across thousands of trials, the same information in different orders yields different outcomes, even when the final dialogue contains equivalent task-relevant information. This order effect suggests later clarification is treated as extra context rather than a corrective signal: it refines a stale task state without invalidating it. Coding tasks are especially vulnerable, suggesting early assumptions get embedded in structured artifacts such as interfaces and control flow. Standard prompting and memory strategies do not reliably help: summaries can collapse ambiguity, and chain-of-thought can reduce explicit wrong commitment in reasoning traces without improving final task success. These findings motivate uncertainty-preserving state management. If assistants cannot let go of early interpretations, robustness cannot rely on post hoc correction alone; it must keep ambiguous early turns from hardening into one task state. Assistants should hold tentative hypotheses while ambiguity remains, ask before executing when high-impact ambiguity persists, and rebuild from a revised state when later evidence invalidates an earlier reading. Rather than one prompting fix, we aim to redirect research for interactive LLMs from retaining more context toward preserving uncertainty.

cs.AI↗

arXiv2026

Repeated post-training is not Self-improving: Diagnosing Scientific Amnesia in Continual DPO Pipelines

Industrial LLM teams often ship behavior updates by repeatedly DPO-training a base model on sequences of related preference-data campaigns. The dominant failure mode in this regime is not always classical catastrophic forgetting: a pipeline may preserve previously learned behaviors while still failing to accumulate reusable methodological knowledge about how to train the next campaign. We call this failure mode scientific amnesia. This paper turns that practitioner intuition into a measurable industrial problem. We contribute: (i) a diagnostic suite for amnesia, (ii) a Program-based pipeline that chains FSDP-sharded DPO checkpoints across Qwen2.5-7B-Instruct runs, (iii) a 30-campaign HumanEval subdomain benchmark, and (iv) a comparative diagnostic study of five strategy proposers: random memory, rule-based scheduling, retrieval-only memory, warm-start Bayesian optimization, and MSCL, a meta-scientific memory and reasoner candidate. Across a single-seed 5-condition * 3-step real-LM chain, 4 of 5 candidates degrade in step-level peak pass@1, including MSCL; only the deliberately conservative rule-based schedule improves. Follow-up pilots qualify rather than overturn this finding: in a heterogeneous chain, MSCL is the only completed candidate that improves, whereas in a small multi-seed homogeneous sweep, retrieval-only has the best mean Delta and no pairwise candidate gap is statistically distinguishable. The contribution is therefore diagnostic, not a claim that MSCL solves the problem: scientific amnesia is observable in a production-like continual-DPO pipeline, and conclusions about interventions depend sharply on chain regime, evaluator design, and seed coverage.

cs.AI↗

arXiv2026

Self-Improvement Can Self-Regress: The Rise-and-Collapse Failure Mode of LLM Self-Training

Self-improvement can self-regress. In REINFORCE post-training for code, a model can quickly improve on its optimized metric and then collapse within the same training campaign. We study this in a controlled multi-seed testbed using Qwen-2.5-3B and Qwen-2.5-7B, trained on competitive-programming tasks with binary CodeGrader reward across 10 sequential 20-step campaigns. Across campaigns, pass@1 shows a robust rise-then-collapse pattern: it peaks within tens of gradient steps and then falls back, sometimes to near zero. This is not cross-task catastrophic forgetting, but within-task policy over-optimization on a fixed distribution; KL- and EWC-style constraints do not prevent it. We ask where the control loop should sit. We compare three levels: CARE, a between-campaign memory mechanism with a capability posterior, transfer gate, and regression-aware belief revision; ES, a within-campaign early-stop rule that rolls forward the peak checkpoint and sets the next budget to peak_step+3; and GRPO, which changes the RL update using group-relative reward normalization. The answer is regime-dependent. On Qwen-2.5-3B, where naive REINFORCE is fragile, CARE v2 nearly doubles end-of-chain pass@1 from 4.9% to 9.5%, with paired bootstrap 95% CI [+0.4,+8.9] and gains in 4/5 seeds. On Qwen-2.5-7B, CARE reaches parity with naive REINFORCE, 13.8% vs. 11.8%, while ES reaches 22.2% [14.1,28.0]. Out-of-the-box GRPO reaches 20.7% [15.7,25.1], nearly matching REINFORCE+ES. GRPO raises the floor but does not remove the cliff. Its 7B gain mainly comes from better between-campaign carryover, while the within-campaign peak-to-end gap remains about 17 points under both REINFORCE and GRPO. GRPO+ES gives mixed evidence: 2/3 seeds improve, but one final cliff lowers the mean to 17.0% [0.0,28.1]. A Gemma-3-4B pilot shows the same signature, suggesting the phenomenon is not limited to Qwen.

cs.AI↗

arXiv2025

Towards Continuous Intelligence Growth: Self-Training, Continual Learning, and Dual-Scale Memory in SuperIntelliAgent

We introduce SuperIntelliAgent, an agentic learning framework that couples a trainable small diffusion model (the learner) with a frozen large language model (the verifier) to enable continual intelligence growth through self-supervised interaction. Unlike conventional supervised fine-tuning, SuperIntelliAgent learns autonomously without annotation: the learner generates candidate outputs, the verifier evaluates them through step-by-step reasoning, and their interaction produces chosen/rejected pairs for Direct Preference Optimization (DPO). This converts each input into a pseudo-training signal for continual improvement. The framework integrates dual-scale memory: short-term in-context memory that preserves reasoning traces across refinement cycles, and long-term memory that consolidates acquired knowledge through lightweight on-the-fly fine-tuning. A replay buffer retains samples that show verifiable progress and replays them as auxiliary supervision, reinforcing recent learning while forming adaptive curricula. SuperIntelliAgent is infrastructure-agnostic and can be plugged into existing agentic frameworks while turning ordinary inference loops into a lifelong optimization process. We posit that pairing a trainable learner with a reasoning-capable verifier forms a minimal reliable unit of growing intelligence, as paired feedback and partial-history replay yield richer learning curricula and stronger preference alignment. With a small number of automatically generated DPO pairs, the learner improves across all benchmarks, indicating that this mechanism provides a promising direction for continual intelligence accumulation and real-world deployment.

cs.AI↗

arXiv2024

Multi-User Chat Assistant (MUCA): a Framework Using LLMs to Facilitate Group Conversations

Recent advancements in large language models (LLMs) have provided a new avenue for chatbot development. Most existing research, however, has primarily centered on single-user chatbots that determine "What" to answer. This paper highlights the complexity of multi-user chatbots, introducing the 3W design dimensions: "What" to say, "When" to respond, and "Who" to answer. Additionally, we proposed Multi-User Chat Assistant (MUCA), an LLM-based framework tailored for group discussions. MUCA consists of three main modules: Sub-topic Generator, Dialog Analyzer, and Conversational Strategies Arbitrator. These modules jointly determine suitable response contents, timings, and appropriate addressees. This paper further proposes an LLM-based Multi-User Simulator (MUS) to ease MUCA's optimization, enabling faster simulation of conversations between the chatbot and simulated users, and speeding up MUCA's early development. In goal-oriented conversations with a small to medium number of participants, MUCA demonstrates effectiveness in tasks like chiming in at appropriate timings, generating relevant content, and improving user engagement, as shown by case studies and user studies.

cs.CL↗

arXiv2024

NeuralMatrix: Compute the Entire Neural Networks with Linear Matrix Operations for Efficient Inference

The inherent diversity of computation types within the deep neural network (DNN) models often requires a variety of specialized units in hardware processors, which limits computational efficiency, increasing both inference latency and power consumption, especially when the hardware processor needs to support and execute different neural networks. In this study, we introduce NeuralMatrix, which elastically transforms the computations of entire DNNs into linear matrix operations. This transformation allows seamless execution of various DNN models all with matrix operations and paves the way for running versatile DNN models with a single General Matrix Multiplication (GEMM) accelerator.Extensive experiments with both CNN and transformer-based models demonstrate the potential of NeuralMatrix to accurately and efficiently execute a wide range of DNN models, achieving 2.17-38.72 times computation efficiency (i.e., throughput per power) compared to CPUs, GPUs, and SoC platforms. This level of efficiency is usually only attainable with the accelerator designed for a specific neural network.

cs.LG↗

arXiv2024

Order of Compression: A Systematic and Optimal Sequence to Combinationally Compress CNN

Model compression has gained significant popularity as a means to alleviate the computational and memory demands of machine learning models. Each compression technique leverages unique features to reduce the size of neural networks. Although intuitively combining different techniques may enhance compression effectiveness, we find that the order in which they are combined significantly influences performance. To identify the optimal sequence for compressing neural networks, we propose the Order of Compression, a systematic and optimal sequence to apply multiple compression techniques in the most effective order. We start by building the foundations of the orders between any two compression approaches and then demonstrate inserting additional compression between any two compressions will not break the order of the two compression approaches. Based on the foundations, an optimal order is obtained with topological sorting. Validated on image-based regression and classification networks across different datasets, our proposed Order of Compression significantly reduces computational costs by up to 859 times on ResNet34, with negligible accuracy loss (-0.09% for CIFAR10) compared to the baseline model. We believe our simple yet effective exploration of the order of compression will shed light on the practice of model compression.

cs.LG↗

arXiv2024

BatchPrompt: Accomplish more with less

As the ever-increasing token limits of large language models (LLMs) have enabled long context as input, prompting with single data samples might no longer an efficient way. A straightforward strategy improving efficiency is to batch data within the token limit (e.g., 8k for gpt-3.5-turbo; 32k for GPT-4), which we call BatchPrompt. We have two initial observations for prompting with batched data. First, we find that prompting with batched data in longer contexts will inevitably lead to worse performance, compared to single-data prompting. Second, the performance of the language model is significantly correlated with the positions and order of the batched data, due to the corresponding change in decoder context. To retain efficiency and overcome performance loss, we propose Batch Permutation and Ensembling (BPE), and a novel Self-reflection-guided EArly Stopping (SEAS) technique. Our comprehensive experimental evaluation demonstrates that BPE can boost the performance of BatchPrompt with a striking margin on a range of popular NLP tasks, including question answering (Boolq), textual entailment (RTE), and duplicate questions identification (QQP). These performances are even competitive with/higher than single-data prompting(SinglePrompt), while BatchPrompt requires much fewer LLM calls and input tokens (For SinglePrompt v.s. BatchPrompt with batch size 32, using just 9%-16% the number of LLM calls, Boolq accuracy 90.6% to 90.9% with 27.4% tokens, QQP accuracy 87.2% to 88.4% with 18.6% tokens, RTE accuracy 91.5% to 91.1% with 30.8% tokens). To the best of our knowledge, this is the first work to technically improve prompting efficiency of large language models. We hope our simple yet effective approach will shed light on the future research of large language models. The code will be released.

cs.CL↗

arXiv2024

Learning How To Ask: Cycle-Consistency Refines Prompts in Multimodal Foundation Models

When LLMs perform zero-shot inference, they typically use a prompt with a task specification, and generate a completion. However, there is no work to explore the possibility of the reverse - going from completion to task specification. In this paper, we employ both directions to perform cycle-supervised learning entirely in-context. Our goal is to create a forward map f : X -> Y (e.g. image -> generated caption), coupled with a backward map g : Y -> X (e.g. caption -> generated image) to construct a cycle-consistency "loss" (formulated as an update to the prompt) to enforce g(f(X)) ~= X. The technique, called CyclePrompt, uses cycle-consistency as a free supervisory signal to iteratively craft the prompt. Importantly, CyclePrompt reinforces model performance without expensive fine-tuning, without training data, and without the complexity of external environments (e.g. compilers, APIs). We demonstrate CyclePrompt in two domains: code generation and image captioning. Our results on the HumanEval coding benchmark put us in first place on the leaderboard among models that do not rely on extra training data or usage of external environments, and third overall. Compared to the GPT4 baseline, we improve accuracy from 80.5% to 87.2%. In the vision-language space, we generate detailed image captions which outperform baseline zero-shot GPT4V captions, when tested against natural (VQAv2) and diagrammatic (FigureQA) visual question-answering benchmarks. To the best of our knowledge, this is the first use of self-supervised learning for prompting.

cs.CL↗

arXiv2022

NYU-VPR: Long-Term Visual Place Recognition Benchmark with View Direction and Data Anonymization Influences

Visual place recognition (VPR) is critical in not only localization and mapping for autonomous driving vehicles, but also in assistive navigation for the visually impaired population. To enable a long-term VPR system on a large scale, several challenges need to be addressed. First, different applications could require different image view directions, such as front views for self-driving cars while side views for the low vision people. Second, VPR in metropolitan scenes can often cause privacy concerns due to the imaging of pedestrian and vehicle identity information, calling for the need for data anonymization before VPR queries and database construction. Both factors could lead to VPR performance variations that are not well understood yet. To study their influences, we present the NYU-VPR dataset that contains more than 200,000 images over a 2km by 2km area near the New York University campus, taken within the whole year of 2016. We present benchmark results on several popular VPR algorithms showing that side views are significantly more challenging for current VPR methods while the influence of data anonymization is almost negligible, together with our hypothetical explanations and in-depth analysis.

cs.CV↗

arXiv2022

IntentVizor: Towards Generic Query Guided Interactive Video Summarization

The target of automatic video summarization is to create a short skim of the original long video while preserving the major content/events. There is a growing interest in the integration of user queries into video summarization or query-driven video summarization. This video summarization method predicts a concise synopsis of the original video based on the user query, which is commonly represented by the input text. However, two inherent problems exist in this query-driven way. First, the text query might not be enough to describe the exact and diverse needs of the user. Second, the user cannot edit once the summaries are produced, while we assume the needs of the user should be subtle and need to be adjusted interactively. To solve these two problems, we propose IntentVizor, an interactive video summarization framework guided by generic multi-modality queries. The input query that describes the user's needs are not limited to text but also the video snippets. We further represent these multi-modality finer-grained queries as user `intent', which is interpretable, interactable, editable, and can better quantify the user's needs. In this paper, we use a set of the proposed intents to represent the user query and design a new interactive visual analytic interface. Users can interactively control and adjust these mixed-initiative intents to obtain a more satisfying summary through the interface. Also, to improve the summarization quality via video understanding, a novel Granularity-Scalable Ego-Graph Convolutional Networks (GSE-GCN) is proposed. We conduct our experiments on two benchmark datasets. Comparisons with the state-of-the-art methods verify the effectiveness of the proposed framework. Code and dataset are available at https://github.com/jnzs1836/intent-vizor.

cs.CV↗

arXiv2022

CitySurfaces: City-Scale Semantic Segmentation of Sidewalk Materials

While designing sustainable and resilient urban built environment is increasingly promoted around the world, significant data gaps have made research on pressing sustainability issues challenging to carry out. Pavements are known to have strong economic and environmental impacts; however, most cities lack a spatial catalog of their surfaces due to the cost-prohibitive and time-consuming nature of data collection. Recent advancements in computer vision, together with the availability of street-level images, provide new opportunities for cities to extract large-scale built environment data with lower implementation costs and higher accuracy. In this paper, we propose CitySurfaces, an active learning-based framework that leverages computer vision techniques for classifying sidewalk materials using widely available street-level images. We trained the framework on images from New York City and Boston and the evaluation results show a 90.5% mIoU score. Furthermore, we evaluated the framework using images from six different cities, demonstrating that it can be applied to regions with distinct urban fabrics, even outside the domain of the training data. CitySurfaces can provide researchers and city agencies with a low-cost, accurate, and extensible method to collect sidewalk material data which plays a critical role in addressing major sustainability issues, including climate change and surface water management.

cs.CV↗

arXiv2021

SCIDA: Self-Correction Integrated Domain Adaptation from Single- to Multi-label Aerial Images

Most publicly available datasets for image classification are with single labels, while images are inherently multi-labeled in our daily life. Such an annotation gap makes many pre-trained single-label classification models fail in practical scenarios. This annotation issue is more concerned for aerial images: Aerial data collected from sensors naturally cover a relatively large land area with multiple labels, while annotated aerial datasets, which are publicly available (e.g., UCM, AID), are single-labeled. As manually annotating multi-label aerial images would be time/labor-consuming, we propose a novel self-correction integrated domain adaptation (SCIDA) method for automatic multi-label learning. SCIDA is weakly supervised, i.e., automatically learning the multi-label image classification model from using massive, publicly available single-label images. To achieve this goal, we propose a novel Label-Wise self-Correction (LWC) module to better explore underlying label correlations. This module also makes the unsupervised domain adaptation (UDA) from single- to multi-label data possible. For model training, the proposed model only uses single-label information yet requires no prior knowledge of multi-labeled data; and it predicts labels for multi-label aerial images. In our experiments, trained with single-labeled MAI-AID-s and MAI-UCM-s datasets, the proposed model is tested directly on our collected Multi-scene Aerial Image (MAI) dataset.

cs.CV↗

arXiv2021

ERA: Entity Relationship Aware Video Summarization with Wasserstein GAN

Video summarization aims to simplify large scale video browsing by generating concise, short summaries that diver from but well represent the original video. Due to the scarcity of video annotations, recent progress for video summarization concentrates on unsupervised methods, among which the GAN based methods are most prevalent. This type of methods includes a summarizer and a discriminator. The summarized video from the summarizer will be assumed as the final output, only if the video reconstructed from this summary cannot be discriminated from the original one by the discriminator. The primary problems of this GAN based methods are two folds. First, the summarized video in this way is a subset of original video with low redundancy and contains high priority events/entities. This summarization criterion is not enough. Second, the training of the GAN framework is not stable. This paper proposes a novel Entity relationship Aware video summarization method (ERA) to address the above problems. To be more specific, we introduce an Adversarial Spatio Temporal network to construct the relationship among entities, which we think should also be given high priority in the summarization. The GAN training problem is solved by introducing the Wasserstein GAN and two newly proposed video patch/score sum losses. In addition, the score sum loss can also relieve the model sensitivity to the varying video lengths, which is an inherent problem for most current video analysis tasks. Our method substantially lifts the performance on the target benchmark datasets and exceeds the current leaderboard Rank 1 state of the art CSNet (2.1% F1 score increase on TVSum and 3.1% F1 score increase on SumMe). We hope our straightforward yet effective approach will shed some light on the future research of unsupervised video summarization.

cs.CV↗

arXiv2021

Rethinking Crowdsourcing Annotation: Partial Annotation with Salient Labels for Multi-Label Image Classification

Annotated images are required for both supervised model training and evaluation in image classification. Manually annotating images is arduous and expensive, especially for multi-labeled images. A recent trend for conducting such laboursome annotation tasks is through crowdsourcing, where images are annotated by volunteers or paid workers online (e.g., workers of Amazon Mechanical Turk) from scratch. However, the quality of crowdsourcing image annotations cannot be guaranteed, and incompleteness and incorrectness are two major concerns for crowdsourcing annotations. To address such concerns, we have a rethinking of crowdsourcing annotations: Our simple hypothesis is that if the annotators only partially annotate multi-label images with salient labels they are confident in, there will be fewer annotation errors and annotators will spend less time on uncertain labels. As a pleasant surprise, with the same annotation budget, we show a multi-label image classifier supervised by images with salient annotations can outperform models supervised by fully annotated images. Our method contributions are 2-fold: An active learning way is proposed to acquire salient labels for multi-label images; and a novel Adaptive Temperature Associated Model (ATAM) specifically using partial annotations is proposed for multi-label image classification. We conduct experiments on practical crowdsourcing data, the Open Street Map (OSM) dataset and benchmark dataset COCO 2014. When compared with state-of-the-art classification methods trained on fully annotated images, the proposed ATAM can achieve higher accuracy. The proposed idea is promising for crowdsourcing data annotation. Our code will be publicly available.

cs.CV↗

arXiv2021

Aerial Scene Understanding in The Wild: Multi-Scene Recognition via Prototype-based Memory Networks

Aerial scene recognition is a fundamental visual task and has attracted an increasing research interest in the last few years. Most of current researches mainly deploy efforts to categorize an aerial image into one scene-level label, while in real-world scenarios, there often exist multiple scenes in a single image. Therefore, in this paper, we propose to take a step forward to a more practical and challenging task, namely multi-scene recognition in single images. Moreover, we note that manually yielding annotations for such a task is extraordinarily time- and labor-consuming. To address this, we propose a prototype-based memory network to recognize multiple scenes in a single image by leveraging massive well-annotated single-scene images. The proposed network consists of three key components: 1) a prototype learning module, 2) a prototype-inhabiting external memory, and 3) a multi-head attention-based memory retrieval module. To be more specific, we first learn the prototype representation of each aerial scene from single-scene aerial image datasets and store it in an external memory. Afterwards, a multi-head attention-based memory retrieval module is devised to retrieve scene prototypes relevant to query multi-scene images for final predictions. Notably, only a limited number of annotated multi-scene images are needed in the training phase. To facilitate the progress of aerial scene recognition, we produce a new multi-scene aerial image (MAI) dataset. Experimental results on variant dataset configurations demonstrate the effectiveness of our network. Our dataset and codes are publicly available.

cs.CV↗