jina-embeddings-v4 is a 3.8B parameter unified multimodal embedding model supporting single/multi-vector representations for cross-modal retrieval.

Michael Günther, Saba Sturua, Mohammad Kalim Akram et al.

Combines fast experiments with Bayesian optimization to enhance long-term outcomes, reducing experiment time by 60%.

Qing Feng, Samuel Daulton, Benjamin Letham et al.

Proposes a relation-based taxonomy for click models, introducing three key design choices to unify PGMs and NNs across interfaces.

Jingwei Kang, Maarten de Rijke, Santiago de Leon-Martinez et al.

IndexTTS2 achieves precise duration control and emotional expressiveness in zero-shot autoregressive TTS, outperforming state-of-the-art models with specific metrics.

Siyi Zhou, Yiquan Zhou, Yi He et al.

Proposed a variational flow matching (VFM) framework for controlled molecular generation, incorporating equivariance to ensure invariance under rotations, translations, and permutations, achieving state-of-the-art results.

Floor Eijkelboom, Heiko Zimmermann, Sharvaree Vadgama et al.

RLPR leverages LLM's token probabilities as rewards, eliminating the need for verifiers, significantly boosting reasoning capabilities.

Tianyu Yu, Bo Ji, Shouli Wang et al.

Deep Research agents enhance complex task handling via dynamic reasoning and multi-hop retrieval.

Yuxuan Huang, Yihang Chen, Haozheng Zhang et al.

This paper introduces a CNN-based 3D near-field source localization method, significantly outperforming MUSIC in accuracy and computational speed.

Parisa Ramezani, Seyed Jalaleddin Mousavirad, Mattias O'Nils et al.

This study systematically evaluates 17 Indic languages using BPE and Unigram LM, highlighting script normalization and clustering as key improvements.

Maharaj Brahma, N J Karthika, Rajat Verma et al.

The study reveals quality issues in multilingual speech datasets, emphasizing the need for sociolinguistic awareness and proactive language planning.

Mingfei Lau, Qian Chen, Yeming Fang et al.

Dex1B uses generative models to create 1 billion demonstrations for dexterous manipulation, enhancing diversity and quality in grasping and articulation tasks.

Jianglong Ye, Keyi Wang, Chengjing Yuan et al.

MemBench: a multi-scenario, multi-level benchmark evaluating LLMs' memory via accuracy, recall, capacity, and efficiency.

Haoran Tan, Zeyu Zhang, Chen Ma et al.

This study introduces wavelet-based frequency augmentation to improve AI-generated video detection, boosting cross-model accuracy by over 12%.

Riccardo Corvi, Davide Cozzolino, Ekta Prashnani et al.

TabArena is a continuously maintained benchmark for tabular ML, combining curated datasets and models, advancing evaluation standards.

Nick Erickson, Lennart Purucker, Andrej Tschalzev et al.

CR-DAgger combines compliant intervention and residual policy learning to improve contact-rich manipulation success by 64% with minimal human corrections.

Xiaomeng Xu, Yifan Hou, Chendong Xin et al.

GFlowGR, a GFlowNet-based fine-tuning framework, effectively mitigates exposure bias in generative recommendation.

Yejing Wang, Shengyu Zhou, Jinyu Lu et al.

Proposes OpenBench for evaluating open-vocabulary segmentation, with OVSNet achieving SOTA, outperforming existing methods by ~10%.

Yong Liu, SongLi Wu, Sule Bai et al.

WAMI introduces MLIR-based WebAssembly dialects for direct high-level code generation, maintaining abstraction and supporting new features efficiently.

Byeongjee Kang, Harsh Desai, Limin Jia et al.

This paper uncovers emergent symbolic mechanisms in VLMs using spatial indexing (position IDs) to solve the binding problem, validated via causal mediation.

Rim Assouel, Declan Campbell, Yoshua Bengio et al.

Introduces Diffusion Steering via Reinforcement Learning (DSRL), enabling sample-efficient online adaptation of diffusion-based robotic policies.

Andrew Wagenmaker, Mitsuhiko Nakamoto, Yunchu Zhang et al.