Trending research and the full catalog - each paper linked to the benchmarks, methods, and models it introduces.
Filtering here covers the 2,000 most recent papers, as much as one page can hold in memory. See the full index of 22,779 papers.
1 May 2026
Point cloud stands as the most widely adopted format for representing 3D shapes and scenes due to its simplicity and geometric fidelity. However, its inherent unordered and irregular nature, exacerbated by sensor noise and occlusions, introduces unique challenges for machine…
1 May 2026
Q-learning is a fundamental algorithmic primitive in reinforcement learning. This paper develops a new framework for analyzing linear Q-learning from a switching linear system (SLS) viewpoint, where linear Q-learning denotes Q-learning with linear function approximation.
1 May 2026
In deep networks with small initialization, training can exhibit long plateaus separated by sharp feature-acquisition transitions. Whereas shallow nonlinear networks and deep linear networks are well studied, extending these analyses to deep nonlinear networks remains…
1 May 2026
Free-form legal essay evaluation in NLP treats expert inter-rater stability as a single ceiling number, and treats LLM-judge agreement with that ceiling as evidence of judge stability.
1 May 2026
Shared-state federated computations combine client-local tensor computation, mergeable aggregation into shared state, and shared-only post-processing. We introduce a typed tensor language for this class of computations.
1 May 2026
Post-hoc explainable AI (XAI) methods usually return one attribution map, even when the model represents uncertainty in its parameters. We define the \emph{explanation distribution} as the distribution of attribution maps obtained from sampled models.
1 May 2026
We develop a unified Lyapunov-integral quadratic constraint (IQC) framework for establishing uniform stability of first-order accelerated optimization algorithms in the $β$-smooth and $γ$-strongly convex regime.
1 May 2026
Inverse-multiquadric (IMQ) kernel sections decay at infinity. Can polynomial alignment add persistent directional responses while preserving universal approximation? The \yat{} (Yat) kernel answers this question by multiplying IMQ distance by a biased squared inner product.
1 May 2026
Federated differentially private protocols can communicate over many adaptive rounds and reuse each client's local samples. Existing lower bound arguments for federated DP are often restricted to noninteractive protocols or fresh batch decompositions, so the fundamental…
Jian Yang, Ruibin Yuan, Yizhi Li · 21 Apr 2026
TACO is a self-evolving compression framework that automatically discovers and refines compression rules from interaction trajectories to improve long-horizon agent performance while reducing token overhead.
Mingqiao Ye, Afshin Dehghan, Roman Bachmann · 16 Apr 2026
Tokenization is a key component of autoregressive (AR) generative models, converting raw data into more manageable units for modeling.
14 Apr 2026
Large Language Models (LLMs) are increasingly used to translate the technical outputs of eXplainable Artificial Intelligence (XAI) methods into accessible natural-language explanations.
Stefan Schulz, Fernando Edelstein, Hannah Dröge · 13 Apr 2026
Real-time free-viewpoint rendering requires balancing multi-camera redundancy with the latency constraints of interactive applications.
Eslam Reda, Sara El-Metwally · 13 Apr 2026
Large Language Models have demonstrated remarkable capabilities in generating contextually relevant and grammatically correct text.
10 Apr 2026
Topic modeling is a branch of Natural Language Processing (NLP) that aims to organize large collections of texts into coherent groups according to word co-occurrence patterns, with Latent Dirichlet Allocation (LDA) remaining one of the most widely used and interpretable…
9 Apr 2026
Agents increasingly modify the procedures by which they solve tasks and improve themselves. Autonomy over improvement, gains in practical capability, and enlargement of computational reach are distinct properties.
7 Apr 2026
Constructing artificial lexicons that are pronounceable, typologically plausible, and semantically structured remains an open challenge in computational linguistics. Existing conlang generators either lack formal phonotactic guarantees or delegate generation to opaque,…
Qihang Yu, Ju He, Liang-Chieh Chen · 6 Apr 2026
Anticipating diverse future states is a central challenge in video world modeling.
Ziwei Liu, Jingkang Yang, Shulin Tian · 2 Apr 2026
Recent streaming video understanding methods increasingly rely on complex memory mechanisms to handle long video streams.
1 Apr 2026
Supervised fine-tuning (SFT) is a common first stage of LLM post-training, teaching the model to follow instructions and shaping its behavior as a helpful assistant. At the same time, SFT may harm the fundamental capabilities of an LLM, particularly after long pretraining: a…
1 Apr 2026
Prompt optimization improves language models without updating their weights by searching for a better system prompt, but its effectiveness varies widely across tasks. We study what makes a task amenable to prompt optimization.
1 Apr 2026
Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to autoregressive generation by enabling parallel token prediction. However, practical dLLM decoding still suffers from high inference latency, which limits deployment.
1 Apr 2026
We study a QA curation pipeline for improving long-context complex reasoning in large language models (LLMs). Our approach, $π^2$, constructs high-quality reasoning data through rigorous QA curation: 1) extracting and expanding tables from Wikipedia, 2) from the collected tables…
1 Apr 2026
RAG-based question-answering (QA) in specialist domains faces a cold-start problem: lack of evaluative benchmarks and absence of labeled data for post-training. We present DoRA (Domain-oriented RAG Assessment), a novel benchmark construction and evaluation framework using only a…