Papers

3,241 in the directory.

Browse AI research papers and methods. Search paper profiles, read recorded summaries and follow source links for the full research.

A–Z Recently synced

Uncertainty-Guided Adverse Weather Restoration via Gated Transformer Network taaft Restoring images degraded by adverse weather remains challenging due to spatially heterogeneous deg… 2026-09-02 published
Uncovering and Mitigating Aggregation-Induced Reward Hacking in Multi-Reward Reinforcement Learning taaft Reinforcement learning fine-tuning of large language models increasingly adopts multiple reward dim… 2026-08-31 published
Uncovering Understanding-Generation Synergy in Native Unified Multimodal Models: From Representation, Task to System taaft While unified multimodal models (UMMs) jointly perform visual understanding and generation within a… 2026-09-01 published
Under One Sun: Multi-Object Generative Perception of Materials and Illumination taaft We introduce Multi-Object Generative Perception (MultiGP), a generative inverse rendering method fo… 2026-03-19 published
Under-Mattress Temporal Sensing for Next-Day Agitation Risk Scoring in Dementia Wards taaft Agitation fluctuates over short time horizons in people living with dementia, yet continuous physio… 2026-08-28 published
Understanding and Defending VLM Jailbreaks via Jailbreak-Related Representation Shift Shopee Large vision-language models (VLMs) often exhibit weakened safety alignment with the integration of… 2026-03-18 published
Understanding and Mitigating the Video-Action Generalization Gap via Temporal Ratio taaft Generative video foundation models exhibit strong compositional priors, yet world-action models (WA… 2026-07-09 published
Understanding Evolution Strategies for LLM Reasoning: Broader Reasoning Coverage than GRPO taaft Evolution Strategies (ES) have recently emerged as a memory-efficient post-training paradigm for LL… 2026-08-27 published
Undetectable Watermarks for Language Models taaft Recent advances in the capabilities of large language models such as GPT-4 have spurred increasing… 2023-05-25 published
Unfold The World: Factorize 4D Properties in Reinforcing Spatial Reasoning taaft Despite the remarkable prowess of Vision-Language Models (VLMs) in general multimodal tasks, they r… 2026-09-03 published
Unfolding Scientific Papers into Multi-Turn Generation Trajectories for Continued Pre-Training taaft A recent line of synthetic-data work reconstructs the thinking behind existing text rather than rew… 2026-08-26 published
Unfolding the Leech Lattice: Fused Multi-Shell Decoding and VRAM Layouts for 2-Bit LLM Weights taaft Leech-lattice vector quantization holds the strongest reported 2-bit quality under its own evaluati… 2026-09-02 published
UniFLM: United Segmentation and Measurement on Fetal Limb Ultrasonic Image taaft Prenatal ultrasound examination is crucial for assessing fetal limb development and detecting conge… 2026-08-27 published
Unifying Conformal Language Tasks with In-Context Ensembles taaft Many NLP tasks, such as summarization and extractive question answering, reduce to retrieving relev… 2026-09-02 published
Unifying Graph Neural Networks Through a Common Layer Equation taaft Graph neural networks are commonly described through family-specific equations whose notation obscu… 2026-08-17 published
Unifying ICL, SFT, KL-Regularized RL Through a Bayesian Lens taaft Supervised fine-tuning (SFT), few-shot in-context learning (ICL), KL-regularized RLHF/RLVR, and on-… 2026-09-04 published
Unifying Linear-Time Attention via Latent Probabilistic Modelling UiPath Transformers have achieved state-of-the-art results across a range of domains, but their quadratic… 2024-02-27 published
Unifying Vision, Text, and Layout for Universal Document Processing taaft We propose Universal Document Processing (UDOP), a foundation Document AI model which unifies text,… 2022-12-05 published
UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph taaft Multi-hop Question Answering over Knowledge Graph~(KGQA) aims to find the answer entities that are… 2022-12-02 published
UniLipi: A Unified Multi-Script OCR for Historical Indic Manuscripts taaft Optical character recognition (OCR) for handwritten Indic manuscripts is essential for large-scale… 2026-08-28 published
UniMate: One Unified Model to Animate Diverse Skeletons taaft Recent advances in automatic rigging now deliver animation-ready 3D assets at scale, yet generating… 2026-09-04 published
UniPR: Unified Object-level Real-to-Sim Perception and Reconstruction from a Single Stereo Pair taaft Perceiving and reconstructing objects from images are critical for real-to-sim transfer tasks, whic… 2026-03-20 published
UniQueR: Unified Query-based Feedforward 3D Reconstruction taaft We present UniQueR, a unified query-based feedforward framework for efficient and accurate 3D recon… 2026-03-24 published
UniSim-SLAM: Feed-Forward SLAM with Unified Sim(3) Optimization taaft Recent geometric foundation models enable feed-forward inference for SLAM, but their predictions ar… 2026-08-03 published
Universal Manipulation Exoskeleton: Learning Compliant Whole-body Policies with Real-time Torque Feedback taaft For robots to work safely in household environments, they need to be compliant and react to torque… 2026-06-12 published
Unleashing Guidance Without Classifiers for Human-Object Interaction Animation taaft Generating realistic human-object interaction (HOI) animations remains challenging because it requi… 2026-03-26 published
Unlocking Lossless Speedups in LLMs via Discrete Diffusion taaft Large Language Models (LLMs) owe much of their success to next-token prediction (NTP), but their au… 2026-09-03 published
Unsupervised Continual Learning with Growing Self-Organizing Maps and Synthetic Replay taaft This work presents a generative continual learning framework based on growing self-organizing maps… 2026-08-27 published
Unsupervised Representation Learning by Predicting Image Rotations taaft Over the last years, deep convolutional neural networks (ConvNets) have transformed the field of co… 2018-03-21 published
Unsupervised vocal dereverberation with diffusion-based generative models taaft Removing reverb from reverberant music is a necessary technique to clean up audio for downstream mu… 2022-11-08 published
Untangling the Mechanisms of Misleading Context in Medical Question Answering taaft Large language models now answer medical questions with expert-level performance. However, the cont… 2026-09-02 published
Unveiling Spectral Mechanisms in Training-Free LLM Text Detection taaft The rapid advancement of Large Language Models (LLMs) makes it increasingly difficult to distinguis… 2026-08-26 published
Urban Boundaries, Social Barriers: A Benchmark and Vision-Centric Framework for Mapping Gated Communities and Equity Implications taaft Communities are fundamental spatial units that shape urban form and social life. Whether a resident… 2026-09-03 published
UrbanGround: From Local Perception to Spatial Agency in a Real-Scale City taaft Multimodal large language models (MLLMs) can interpret a street view, but reliable urban action dep… 2026-08-27 published
uScenes: A Multimodal RGB and 3D Sonar Dataset for Underwater Robot Perception taaft Robust perception is essential for the deployment of autonomous underwater robots. However, optical… 2026-08-28 published
User Feedback Provides a Unique Signal that LLMs Can not Detect taaft Harnessing naturally occurring feedback from user interactions offers a promising learning signal f… 2026-09-02 published