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

RVSD: Retrieval Vision Sparse Decoding for Mitigating Visual Hallucinations in Large Vision-Language Models taaft Large vision-language models have achieved remarkable success in vision-language tasks. However, th… 2026-09-02 published
RW-LoRA: Communication-Efficient Decentralized LoRA Fine-Tuning via Random Walks taaft Parameter-efficient fine-tuning methods such as LoRA have become a standard approach for adapting l… 2026-08-31 published
RWA-PoB: A Credential-Based Proof-of-Backing Framework for Tokenized U.S. Treasury Products taaft Proof of reserves (PoR) can improve transparency for tokenized assets, but aggregate reserve covera… 2026-08-26 published
RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model taaft We present RynnBrain 1.1, a family of embodied foundation models spanning 2B, 9B, and 122B-A10B sca… 2026-07-20 published
S$^2$Prune: Spatially Structured Visual Token Pruning for Multimodal Large Language Models taaft Visual token pruning reduces the inference overhead of multimodal large language models (MLLMs) by… 2026-09-01 published
S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement? taaft Large language models (LLMs) increasingly interact with external environments and accumulate substa… 2026-08-31 published
SABER: Stability-Aware Early Exit for LLM Reasoning via Adversarial Branch Probing taaft Large Reasoning Models (LRMs) achieve strong reasoning capabilities, yet long-chain reasoning becom… 2026-08-28 published
SAC3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistency Intuit Hallucination detection is a critical step toward understanding the trustworthiness of modern langu… 2023-11-03 published
SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense taaft Text-to-Video (T2V) generative models are vulnerable to jailbreak attacks in real-world deployment,… 2026-08-11 published
SafeEvolve: Harness-Policy Co-Evolution from Agent Experience for Safety Alignment taaft The performance of LLM-based agents is jointly shaped by the base model and the harness used when i… 2026-09-02 published
SafeRI: Recognition and Intervention for Token-Level Safety Intervention in Large Vision Language Models taaft Existing safety alignment methods for vision-language models usually modify the model behavior glob… 2026-09-03 published
Safety by Design: Realized-Cost Constraints for Contextual Bandits with Continuous Actions taaft Contextual bandits are a standard framework for sequential decision-making under uncertainty, with… 2026-08-27 published
Safin-1: Safety from Within through Memory-Native State Evolution taaft Long-horizon complex tasks require foundation models to accumulate information, maintain internal s… 2026-08-31 published
SAGE: State-Grounded, Abstention-Aware Evaluation of Task-Oriented Dialogue Agents taaft Evaluating task-oriented dialogue agents requires judging not merely whether a reply reads well but… 2026-08-31 published
SAGE: Subpopulation-Aware Generative Enhancement for Mitigating Spurious Correlations taaft Spurious correlations pose a significant challenge to the robustness of modern machine learning. Th… 2026-09-01 published
SALA: Semantic-Aware Logical Alignment for Complex Reasoning in In-Context Learning taaft Effective in-context learning (ICL) for complex reasoning relies on selecting the right demonstrati… 2026-09-02 published
Saliency-Depth Conditioning for Zero-Shot Segmentation of Communication-Tower Components in Cluttered UAV Imagery taaft Fine-grained segmentation of communication-tower components in UAV imagery is essential for automat… 2026-08-26 published
SAM3-LoRA: Parameter-Efficient Adaptation of a Concept-Promptable Foundation Model for Multi-Class Structural Defect Segmentation taaft Promptable segmentation foundation models such as SAM3 accept an open-vocabulary text concept and r… 2026-08-31 published
Same Request, Different Boundary: Evaluating Cybersecurity Assistance across Conversational Contexts taaft Large Language Models (LLMs) can solve complex problems, but their misuse in high-risk domains can… 2026-09-01 published
Same Semantics, Different Outcome: On the Modality Robustness of Multimodal LLMs under Knowledge Conflict taaft Multimodal large language models (MLLMs) are increasingly provided with contextual evidence in hete… 2026-09-01 published
Same Trajectory, Contradictory Rewards (ROBORMBENCH): Paraphrase Fragility in Vision Language Reward Models taaft Vision-language models are increasingly used as reward functions for robotic learning, but this rol… 2026-09-04 published
Sample More, Reflect Less: Self-Refine and Reflexion Lose to Repeated Sampling at Equal Token Cost, from 1.5B to 7B taaft Methods that make a language model plan, criticise and rewrite its own answer, reflect on mistakes,… 2026-07-30 published
Sampling Is All You Need on Modeling Long-Term User Behaviors for CTR Prediction Meituan Rich user behavior data has been proven to be of great value for Click-Through Rate (CTR) predictio… 2022-05-20 published
SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer taaft Generative adversarial networks (GANs) learn a target probability distribution by optimizing a gene… 2023-01-30 published
SandwichQuant: Which Parameters Matter Before and After Quantization? taaft Quantization correction methods usually optimize weights, quantization parameters, or reconstructio… 2026-08-25 published
SatDL: Jointly Optimizing Data Redistribution and Training for Satellite-Based Distributed Learning taaft Satellite-based distributed learning promises to train machine-learning models directly in orbit us… 2026-08-25 published
SATTC: Structure-Aware Label-Free Test-Time Calibration for Cross-Subject EEG-to-Image Retrieval taaft Cross-subject EEG-to-image retrieval for visual decoding is challenged by subject shift and hubness… 2026-03-21 published
SAUF-Net: Structure--Appearance Representation Learning with Uncertainty Feedback for Semi-Supervised Medical Image Segmentation taaft Semi-supervised learning has shown great potential for reducing annotation costs in medical image s… 2026-09-02 published
SAUSS: Stochastic Approximation with Unbiased Simulated Scores for Limited Dependent Variable Models taaft Multinomial choice models allow flexible substitution patterns but become computationally demanding… 2026-08-26 published
SAVeS: Steering Safety Judgments in Vision-Language Models via Semantic Cues taaft Vision-language models (VLMs) are increasingly deployed in real-world and embodied settings where s… 2026-03-19 published
Scaffolding Foundation Models into Physical-World Agents Pushes the Frontier of Long-Horizon Navigation taaft Long-horizon physical-world agents must reason over distant goals while grounding decisions in reli… 2026-08-31 published
Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstruction taaft Online 3D reconstruction models perform poorly on long videos. This happens because regressing pose… 2026-09-03 published
Scalable Bayesian Optimization of Composite Functions for Image-Based Inverse Problems in Materials Characterization taaft Estimating physical parameters from scientific images is a common inverse problem in materials char… 2026-09-02 published
Scalable Detection of Fossil Palynomorphs in Multifocal Digital Microscopy Images taaft Palynomorphs (microscopic, organic-walled fossils such as pollen, spores, and dinoflagellates) are… 2026-09-04 published
Scalable Differential Privacy with Certified Robustness in Adversarial Learning Apple In this paper, we aim to develop a scalable algorithm to preserve differential privacy (DP) in adve… 2019-03-23 published
Scalable Direction-Following TTS via Voice Impression-Guided Pseudo Triplet Construction taaft Voice actors often re-read the same script while modifying their delivery in response to performanc… 2026-09-02 published