paperlist.ai

AI 顶会论文

AI 顶会论文库

检索 30+ 个顶会的论文，包括 NeurIPS、ICLR、ICML、CVPR、ACL、AAAI 等。输入关键词筛选，打开任意一篇查看摘要、作者和链接。

arXiv

Visualizing High-Dimensional Graph Embeddings via Informed Multi-View Projections

Ya Ji, Xuefeng Li, Timo Brand, Jacob Miller, Peng Zhang, Stephen Kobourov, Yifan Hu

Graphs are commonly visualized in 2D, where humans readily interpret spatial relationships, yet such layouts often distort higher-dimensional structure. We propose to embed graphs in high-dimensional space and search for informative 2D viewpoints that optimize aesthetic and readability metrics (e.g., edge crossings and angular resolution), enabled by a novel differentiable surrogate for edge crossings. Numerical experiments show that these viewpoints consistently outperform standard 2D layouts, and can even surpass methods explicitly designed to optimize these metrics. We further introduce DataFly, an interactive system for exploring multiple candidate viewpoints through seamless navigation. A usability study demonstrates that our approach reveals structural patterns that remain hidden in conventional 2D visualizations.

arXiv

OLIVE: Online Low-Rank Incremental Learning for Efficient Adaptive Exoskeletons

Dong Liu, Yanxuan Yu, Ben Lengerich, Tong Geng, Ying Nian Wu

Wearable exoskeleton systems hold promise for restoring mobility in individuals with physical impairments, yet most existing controllers rely on static gait policies that cannot adapt to dynamic real-world environments or individual user characteristics. We present OLIVE (Online Low-rank Incremental Learning for Efficient Adaptive Exoskeletons), a parameter-efficient online adaptation framework that continuously personalizes exoskeleton control during deployment. OLIVE decomposes the adaptive component of the control policy into a low-rank residual form $ΔW = A_t B_t^\top$ with rank $r \ll \min(d,k)$, reducing the online update cost from $\mathcal{O}(dk)$ to $\mathcal{O}(r(d+k))$ while preserving the stability of a pretrained base controller $W_0$. Parameters are updated through a reward-shaped policy gradient driven purely by on-body sensor feedback, including EMG, IMU, and vibration signals, eliminating dependence on offline reference trajectories. A gating mechanism modulates the strength of personalization based on the contextual state, while a dynamic rank scheduler adapts the update dimensionality to terrain complexity. It allocates minimal capacity on simple flat terrain and expands to higher-rank updates on demanding uneven surfaces, enabling robust performance across flat walking, stair navigation, slopes, and uneven terrain. Experiments on the wearable platform demonstrate that OLIVE achieves improvements of 13, 22, and 15 percentage points in gait smoothness, effort reduction, and motion stability over the strongest baseline, respectively. It converges within approximately 1,800 walking steps with an end-to-end latency of 7.4 ms. Our code implementation is available at https://github.com/FastLM/OLIVE.

arXiv

The Range Shrinks, the Threat Remains: Re-evaluating LLM Package Hallucinations on the 2026 Frontier-Model Cohort

Aleksandr Churilov

Spracklen et al. (USENIX Security '25) showed that code-generating large language models hallucinate package names that do not exist on PyPI or npm at rates ranging from 5.2% on commercial models to 21.7% on open-source models, creating an attack surface for slopsquatting -- the registration of malicious packages under hallucinated names. We replicate their methodology on five frontier code-capable LLMs released between October 2025 and March 2026: Claude Sonnet 4.6, Claude Haiku 4.5, GPT-5.4-mini, Gemini 2.5 Pro, and DeepSeek V3.2. Across 199,845 paired Python and JavaScript prompts validated against PyPI and npm master lists, we measure overall hallucination rates between 4.62% (Claude Haiku 4.5) and 6.10% (GPT-5.4-mini) -- an order-of-magnitude compression of the inter-model spread observed by Spracklen, but not a retirement of the threat. Beyond replication, we identify a set of 127 package names (109 on PyPI, 18 on npm) that all five evaluated models invent identically; following coordinated disclosure with PyPI Security and Socket.dev, 53 of these (41 on PyPI, 12 on npm) remain registrable by an attacker after each registry's existing defenses, constituting a model-agnostic supply-chain attack surface that no single-model study can reveal. We further document a Python-over-JavaScript hallucination asymmetry that inverts Spracklen's 2024 finding, identify a Haiku-below-Sonnet inversion within the Anthropic family, and observe a Jaccard-similarity peak between DeepSeek V3.2 and GPT-5.4-mini (J = 0.343) suggestive of shared training-data origins.

arXiv

ArtifactLinker: Linking Scientific Artifacts for Automatic State-of-the-Art Discovery

Haofei Yu, Jiaxuan You, Peter Clark, Bodhisattwa Prasad Majumder, Kyle Richardson

Scientific artifacts such as models and datasets are foundations for research. With the rapid growth of platforms like HuggingFace, researchers now have access to a large number of artifacts. Yet, a key challenge remains: how can we automatically discover the state-of-the-art (SOTA) model for a given dataset by fully leveraging existing artifacts? We formalize this task as automatic SOTA discovery by modeling HuggingFace as an artifact graph, where nodes are models/datasets and edges represent evaluations. We propose ArtifactLinker, a two-stage framework: (1) ranking promising unobserved model--dataset links using Graph Neural Networks (GNNs) or graph-augmented Large Language Models (LLMs), and (2) verifying top-ranked links via coding experiments with LLM-based agents. We further introduce a benchmark named ArtifactBench with 14,053 artifacts and 51,337 relations to evaluate the performance of both stages. Results show that (1) graph structures between existing artifacts are effective for missing link prediction; (2) end-to-end ranking and verification with ArtifactLinker help discover potential SOTA results and research insights.

arXiv

Early Data Exposure Improves Robustness to Subsequent Fine-Tuning

Lawrence Feng, Gaurav R. Ghosal, Jacob Mitchell Springer, Ziqian Zhong, Aditi Raghunathan

How can we train models whose post-trained capabilities survive subsequent fine-tuning? Rather than focusing on downstream interventions to mitigate forgetting of upstream capabilities, we study how upstream training choices - that is, the manner in which a capability is acquired - shape how robustly that capability is retained. We investigate this question in a controlled three-stage language-model pipeline: pretraining, post-training to acquire a target capability, and downstream fine-tuning on a new objective. Across 135M and 1B models, two post-training domains, and two downstream fine-tuning tasks, we find that immediate post-training performance does not reliably predict retention after subsequent fine-tuning: training recipes that look equivalent immediately after post-training can retain the target capability very differently after subsequent fine-tuning. In particular, early exposure - mixing post-training data into pretraining - consistently improves the frontier between retained upstream performance and downstream performance. In compute-matched experiments, where the target data must be allocated between pretraining and post-training, we find that the optimum lies at neither extreme. Together with our other empirical and theoretical findings, this supports the view that post-training drives immediate specialization while early exposure improves robustness to later forgetting. Replay and dropout, typically used to mitigate forgetting as it occurs during fine-tuning, provide complementary gains to early exposure when applied during post-training. Our findings suggest that robustness to subsequent fine-tuning should be treated as a first-class objective of upstream training, addressed preventatively through choices like early exposure rather than reactively during fine-tuning itself.

arXiv

Aggregation in conformal e-classification

Vladimir Vovk

Aggregating conformal predictors is a standard way of balancing their predictive and computational efficiency while retaining their validity, at least approximately. An important advantage of conformal e-predictors is that they are easier to aggregate without sacrificing their validity. This paper studies experimentally cross-conformal e-prediction, which is an existing method of aggregating conformal e-predictors, and its modifications that are conceptually simpler and more flexible.

arXiv

FitText: Evolving Agent Tool Ecologies via Memetic Retrieval

Kyle Zheng, Han Zhang, Renliang Sun, Chenchen Ye, Wei Wang

Efficient reasoning is not only a matter of shortening an answer trace; for tool-using agents, it also depends on whether the agent is reasoning over the right action space. As API ecosystems scale to tens of thousands of endpoints, the semantic gap between user requests and tool documentation makes this problem concrete: static retrieval from the initial query can fail before planning begins, and stronger planning alone cannot recover a missing tool. We study this problem as budgeted test-time retrieval and introduce FitText, a training-free framework that makes the tool interface revisable during execution by generating, refining, and evolving natural-language pseudo-tool descriptions as retrieval probes. FitText supports serial refinement, parallel exploration, and Memetic Retrieval, which adds evolutionary selection, local refinement, and tool memory to avoid redundant search. On StableToolBench (16,464 APIs), Memetic FitText reaches an 84.3% pooled pass rate, improving +26.7 points over static retrieval, +22.2 over Single-Pass, +23.2 over Re-Invoke, and +27.5 over Xu-style root refinement. It leads on every evaluated current model, with gains growing alongside model capability, and produces the largest improvements on ambiguous multi-tool tasks where dynamic re-retrieval restores correct candidates after early mistakes. At 40-way concurrency, parallel population execution keeps batched wall-clock at 1.01x Single-Pass despite the added search work.

arXiv

Statistically-Lossless Quantization of Large Language Models

Michael Helcig, Eldar Kurtic, Dan Alistarh

Model quantization has become essential for efficient large language model deployment, yet existing approaches present clear trade-offs: methods such as GPTQ and AWQ achieve practical compression but are lossy, while lossless techniques preserve fidelity but lack inference acceleration. This paper explores the middle ground of statistically-lossless compression, examining three complementary aspects of what losslessness means for quantized LLMs. First, task-lossless compression preserves zero-shot benchmark accuracy within natural sampling variance and is achievable at aggressive bitwidths. Second, we formalize the stricter notion of distribution-lossless compression, requiring the quantized model's next-token distribution to be practically indistinguishable from the original, and propose the Expected Acceptance Rate (EAR), the maximum token-agreement probability under optimal coupling, as a directly interpretable fidelity metric. For example, EAR >= 0.99 means 99% agreement. Third, we prove a gamma-squared variance law showing that symmetric quantization inflates noise variance by gamma^2 relative to asymmetric quantization, making asymmetric quantization a prerequisite for distribution-lossless fidelity but not for task-level preservation. Through SLQ, a layer-wise non-uniform method with asymmetric quantization and wide bitwidth search, we obtain task-lossless compression at well below 4 bits per parameter, as low as 3.3 bits depending on the model, distribution-lossless compression at 5-6 bits per parameter on average, and inference speedups of 1.7-3.7x compared to FP16 using optimized kernels. Source code is available at [https://github.com/IST-DASLab/SLQ](https://github.com/IST-DASLab/SLQ).

arXiv

Stable GFlowNets with TV Monitoring and Probabilistic Guarantees

Zengxiang Lei, Ananth Shreekumar, Jonathan Rosenthal, Ruoyu Song, Alvaro A. Cardenas, Daniel J. Fremont, Dongyan Xu, Satish Ukkusuri, Z. Berkay Celik

Generative Flow Networks (GFlowNets) sample diverse structured objects in proportion to reward and have been applied to molecular discovery and biological-sequence design, where finding multiple high-quality candidates is more useful than returning a single optimum. Despite their theoretical promise, practical training is often unstable, exhibiting severe loss spikes and mode collapse. To address this, we first assess the sensitivity of GFlowNet objectives, demonstrating that a small Total Variation (TV) distance between the learned and target distributions does not preclude an unbounded training loss. Motivated by this mismatch, we establish converse guarantees by deriving loss-to-TV bounds that certify global fidelity from bounded trajectory balance losses. Lastly, we propose Stable GFlowNets, which leverages our theory to stabilize training via adaptive reference flow and improves the trade-off among mode coverage, robustness, and certifiability.

arXiv

Themis: Training Robust Multilingual Code Reward Models for Flexible Multi-Criteria Scoring

Indraneil Paul, Goran Glavaš, Iryna Gurevych

Reward models (RMs) have become an indispensable fixture of the language model (LM) post-training playbook, enabling policy alignment and test-time scaling. Research on the application of RMs in code generation, however, has been comparatively sparse, with existing work largely focusing on execution feedback. This choice constrains post-training to optimizing functional correctness over self-contained executable code. In this work, we examine the training and evaluation of multilingual, multi-criteria code RMs. To this end, we first compile Themis-CodeRewardBench, a benchmark to evaluate code RMs across five preference dimensions (i.e., criteria) and eight programming languages, on which we profile 50+ code, math, and general-purpose RMs. Observing the limited proficiency of current RMs beyond scoring for functional correctness, we develop Themis-CodePreference, the largest open-source collection of code preferences to date (more than 350k preference pairs), and use it to train Themis-RM, a suite of multilingual code reward models for flexible multi-criteria scoring, ranging in size from 600M to 32B parameters. Our experiments and ablations demonstrate positive scaling trends, strong cross-lingual transfer when training on diverse preferences, and the importance of multi-criteria training for reliable code reward modeling.

arXiv

ZenBrain: A Neuroscience-Inspired 7-Layer Memory Architecture for Autonomous AI Systems

Alexander Bering

ZenBrain is a seven-layer, neuroscience-derived memory architecture for LLM agents that unifies fifteen mechanisms - from Two-Factor synaptic consolidation to a Simulation-Selection sleep loop - under a single MemoryCoordinator: nine foundational algorithms plus six Predictive Memory Architecture components. No system among those we survey integrates more than two of them. Ablating each mechanism separately exposes an effect we call cooperative masking. Under moderate load, fourteen of the fifteen ablations look costless - the architecture reads as mostly dead weight. Raising decay to 0.25/day over 60 days, with no change to the mechanisms, makes nine of the fifteen individually critical (Delta-Q up to -93.7%; Wilcoxon, 10 seeds), five of them moving from exactly 0% to below -89%. The mechanisms form a cooperative survival network, and mild-load ablation systematically underestimates architectural contributions - a caution we conjecture applies beyond ZenBrain. Every ablation table reproduces in under one minute on a laptop (npm install, no API keys). On LongMemEval-500, ZenBrain wins all nine head-to-head answer-quality comparisons (3 competitors x 3 LLM judges) against Letta, Mem0 and A-Mem under Bonferroni-corrected significance (alpha=0.05/18, p_min=6.2e-31, d in [0.18, 0.52]), and reaches 91.3% of a full-context oracle's binary-judge accuracy at 1/106th of the per-query token cost (47.7% vs. 52.2%). Multi-layer routing beats a flat single-layer baseline by +20.7% F1 on LoCoMo; a NoDecay ablation shows principled forgetting costs only Delta-P@5=0.002. Honest scope: LoCoMo's substring-based aggregate F1 favors lexical retrieval (BM25) by metric design, and we do not contest this. ZenBrain's advantages are most pronounced on judge-graded answer quality and cross-session reasoning.

arXiv

Switching Theory for Q-Learning

Donghwan Lee

Q-learning is a fundamental algorithmic primitive in reinforcement learning. This paper develops a new framework for analyzing constant step-size tabular Q-learning from a switching linear system (SLS) viewpoint. In particular, we derive a stochastic SLS representation of the Q-learning error, and a finite-time error analysis through the joint spectral radius (JSR) of the corresponding SLS model, where the JSR is the exact worst-case exponential rate of the associated SLS. To the best of our knowledge, this is the first convergence rate analysis of standard Q-learning whose leading exponential rate is expressed through the JSR. The resulting rate is tied to the intrinsic worst-case exponential rate of the direct SLS representation and can be sharper than row-sum upper bounds when those bounds are conservative. We further prove that the JSR of Q-learning equals the largest spectral radius among the deterministic-policy modes and give an exact linear programming characterization that can be evaluated to any prescribed accuracy.

arXiv

Label-Efficient Bilateral Attention for Parkinson's Disease Screening from Wrist-Worn IMU Signals

Meheru Zannat

Parkinson's disease (PD) is a chronic neurodegenerative disorder. It shows multiple motor symptoms such as tremor, bradykinesia, postural instability, and freezing of gait (FoG). PD is currently diagnosed clinically through physical examination by health-care professionals, which can be time-consuming and highly subjective. Wearable IMU sensors have become a promising gateway for PD detection. We propose a time-interleaving encoder that processes bilateral wrist-worn IMU signals from the public PADS dataset, which consists of three groups, PD (Parkinson's Disease), HC (Healthy Control), and DD (Differential Diagnosis), across a total of 469 subjects. The encoder reaches 93.2%/90.9% accuracy (0.963/0.960 AUROC) on HC-vs-PD and PD-vs-DD; the lower sensitivity on the differential (0.812 vs. 0.994) confirms that separating PD from look-alike disorders is the harder clinical problem. Self-supervised representation learning with a contrastive InfoNCE objective attains 91.6%/89.5% accuracy using only 20% of the labels, within 1.5 points of the full-label ceiling, so near-saturation accuracy is reachable with minimal annotation. For real-time edge deployment we reach 124.5 ms per window on a Raspberry Pi 4.

arXiv

Weighted Bayesian Conformal Prediction

Xiayin Lou, Peng Luo

Machine learning predictors are rarely deployed on data that match the data they were calibrated on. Conformal prediction and its risk-control generalization promise distribution-free guarantees at deployment, but only under exchangeability or a covariate shift whose likelihood ratio is known exactly -- and the estimated-ratio case, the one that occurs in practice, is explicitly open, out of reach of the Bayesian construction available under exchangeability. We reach it from a different starting point: pushing a Dirichlet process prior on the calibration distribution through the likelihood ratio yields the exact Bayesian posterior over the deployed risk. That posterior is exact given the weight function, which at deployment is itself estimated, so we further prove finite-sample upper and lower bounds on the risk the selected threshold actually incurs, in terms of the weight-estimation error and the conditional shift. On synthetic and real covariate shifts, in regression and classification, the realized failure rate then stays close to target where shift-blind selection fails, and what deployment receives is a posterior over the risk of every threshold rather than a single number.

arXiv

Factorization Regret mediates compositional generalization in latent space

John Schwarcz

Are there still barriers to generalization once all of the relevant variables are known? We consider the challenge of generalizing to a novel combination of task-relevant latent variables. To explore this framework, we develop the Cognitive Gridworld, a stationary Partially Observable Markov Decision Process (POMDP) in which observations are generated jointly by multiple latent variables with parametric interactions. This setting allows us to describe Factorization Regret: an information-theoretic quantity that measures the contribution of latent variable interactions to task performance. Using this metric, we first analyze Recurrent Neural Networks (RNNs) that are explicitly provided with the interactions and find that Factorization Regret explains the accuracy gap between Echo State and Fully Trained networks. Additionally, our analysis uncovers a theoretically predicted failure mode, where confidence becomes decoupled from accuracy. These results suggest that utilizing the interactions between relevant variables is a non-trivial capability. We then address a harder regime where the interactions themselves must be learned by an embedding model. Estimating how variables interact while simultaneously inferring their values is a variational inference problem. To explicitly disentangle variable inference from parameter estimation, we develop Representation Classification Chains (RCCs), a novel architecture for learning how latent variables interact. RCCs are capable of learning from sparse and partial reward, provided only for a subset of goal variables. Finally, we demonstrate the usefulness of RCCs in enabling generalization to novel combinations of latent variables through offline learning. In summary, we present a theoretically grounded setting for research, development and evaluation of goal-directed general intelligence.

arXiv

Explaining, Verifying, and Aligning Semantic Hierarchies in Vision-Language Model Embeddings

Gesina Schwalbe, Mert Keser, Moritz Bayerkuhnlein, Edgar Heinert, Annika Mütze, Marvin Keller, Sparsh Tiwari, Georgii Mikriukov, Diedrich Wolter, Jae Hee Lee, Matthias Rottmann

Vision-language model (VLM) encoders such as CLIP enable strong retrieval and zero-shot classification in a shared image-text embedding space, yet the semantic organization of this space is rarely inspected. We present a post-hoc framework to explain, verify, and align the semantic hierarchies induced by a VLM over a given set of child classes. First, we extract a binary hierarchy by agglomerative clustering of class centroids and name internal nodes by dictionary-based matching to a concept bank. Second, we quantify plausibility by comparing the extracted tree against human ontologies using efficient tree- and edge-level consistency measures, and we evaluate utility via explainable hierarchical tree-traversal inference with uncertainty-aware early stopping (UAES). Third, we propose an ontology-guided post-hoc alignment method that learns a lightweight embedding-space transformation, using UMAP to generate target neighborhoods from a desired hierarchy. Across 13 pretrained VLMs and 4 image datasets, our method finds systematic modality differences: image encoders are more discriminative, while text encoders induce hierarchies that better match human taxonomies. Overall, the results reveal a persistent trade-off between zero-shot accuracy and ontological plausibility and suggest practical routes to improve semantic alignment in shared embedding spaces.

arXiv

Estimating Condition Number with Graph Neural Networks

Erin Carson, Xinye Chen

In this paper, we propose a fast method for estimating the condition number of sparse matrices using graph neural networks (GNNs). For efficient deployment of GNNs, we introduce a graph feature construction with $\mathrm{O}(\mathrm{nnz} + n)$ complexity, where $\mathrm{nnz}$ is the number of non-zero elements in the matrix and $n$ denotes the matrix dimension. We propose two schemes for estimating the matrix condition number using GNNs; one follows by decomposing the condition number and predicts the relatively more computationally intensive part $\|\mathbf{A}^{-1}\|$, without explicitly forming the inverse, while the other is to predict the whole condition number $κ$. Our approach can be extended to an arbitrary norm. Extensive experiments are conducted for the estimation of the 1-norm and 2-norm condition numbers, which show that our method achieves a significant speedup over the traditional numerical estimation methods. Our software for GNN condition number estimator is made publicly available at https://github.com/inEXASCALE/sparse-kappa.

arXiv

Variance reduction in lattice QCD observables via normalizing flows

Ryan Abbott, Denis Boyda, Yang Fu, Daniel C. Hackett, Gurtej Kanwar, Fernando Romero-López, Phiala E. Shanahan, Julian M. Urban

Normalizing flows can be used to construct unbiased, reduced-variance estimators for lattice field theory observables that are defined by a derivative with respect to action parameters. This work implements the approach for observables involving gluonic operator insertions in the SU(3) Yang-Mills theory and two-flavor Quantum Chromodynamics (QCD) in four space-time dimensions. Variance reduction by factors of $10$-$60$ is achieved in glueball correlation functions and in gluonic matrix elements related to hadron structure, with demonstrated computational advantages. The observed variance reduction is found to be approximately independent of the lattice volume, so that volume transfer can be utilized to minimize training costs.

arXiv

Doubly Adaptive Channel and Spatial Attention for Semantic Image Communication by IoT Devices

Soroosh Miri, Sepehr Abolhasani, Shahrokh Farahmand, S. Mohammad Razavizadeh, Jiguang He

Internet of Things (IoT) networks face significant challenges such as limited communication bandwidth, constrained computational and energy resources, and highly dynamic wireless channel conditions. Utilization of deep neural networks (DNNs) combined with semantic communication has emerged as a promising paradigm to address these limitations. Deep joint source-channel coding (DJSCC) has recently been proposed to enable semantic communication of images. Building upon the original DJSCC formulation, low-complexity attention-style architectures has been added to the DNNs for further performance enhancement. As a main hurdle, training these DNNs separately for various signal-to-noise ratios (SNRs) will amount to excessive storage or communication overhead, which can not be maintained by small IoT devices. SNR Adaptive DJSCC (ADJSCC), has been proposed to train the DNNs once but feed the current SNR as part of the data to the channel-wise attention mechanism. We improve upon ADJSCC by a simultaneous utilization of doubly adaptive channel-wise and spatial attention modules at both transmitter and receiver. These modules dynamically adjust to varying channel conditions and spatial feature importance, enabling robust and efficient feature extraction and semantic information recovery. Simulation results corroborate that our proposed doubly adaptive DJSCC (DA-DJSCC) significantly improves upon ADJSCC in several performance criteria, while incurring a mild increase in complexity. These facts render DA-DJSCC a desirable choice for semantic communication in performance demanding but low-complexity IoT networks.

arXiv

OATS: Online Data Augmentation for Time Series Foundation Models

Junwei Deng, Chang Xu, Jiaqi W. Ma, Ming Jin, Chenghao Liu, Xu Zhang, Li Zhao, Jiang Bian

Time Series Foundation Models (TSFMs) are a powerful paradigm for time series analysis and are often enhanced by synthetic data augmentation to improve the training data quality. Existing augmentation methods, however, typically rely on heuristics and static paradigms. Motivated by dynamic data optimization, which shows that the contribution of samples varies across training stages, we propose OATS (Online Data Augmentation for Time Series Foundation Models), a principled strategy that generates synthetic data tailored to different training steps. OATS leverages valuable training samples as principled guiding signals and dynamically generates high-quality synthetic data conditioned on them. We further design a diffusion-based framework to produce realistic time series and introduce an explore-exploit mechanism to balance efficiency and effectiveness. Experiments on TSFMs demonstrate that OATS consistently outperforms regular training and yields substantial performance gains over static data augmentation baselines across six validation datasets and two TSFM architectures. The code is available at the link https://github.com/microsoft/TimeCraft.

继续浏览

更多 AI 顶会论文

30+ 个顶会，按会议、年份和主题浏览。

浏览全部会议

进入任一会议和年份，查看完整论文列表。

全部会议 →

搜索论文

按标题、作者或关键词，在 21 万+ 篇论文里搜索。

搜索论文 →