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

From Image to Video, what do we need in multimodal LLMs? taaft Covering from Image LLMs to the more complex Video LLMs, the Multimodal Large Language Models (MLLM… 2024-04-18 published
From Intent to Evidence: Policy-Steered Multi-Strategy Retrieval for Long-Video Agents taaft Existing long-video agents acquire evidence through one uniform behavior, ignoring whether the requ… 2026-08-31 published
From Interaction Traces to Persistent Skills: Online Evolution for Computer-Use Agents taaft Computer-use agents can execute increasingly complex tasks in graphical interfaces, but their inter… 2026-09-04 published
From Interpretability Methods to Interpretable Models taaft More than a decade in, explainable AI (XAI) for computer vision has assembled a mature toolbox: att… 2026-09-04 published
From Language Models to World-Acting Systems: Progress and Limits of Agentic AI across Digital, Social, Virtual, and Physical Environments taaft Large language models become consequential agents when surrounding systems let outputs change exter… 2026-09-04 published
From Language to Behavior: Scaling Sequence Transformers for Industrial Recommendation Ranking with Rec-Native Designs taaft Scaling Transformers has driven large gains in language modeling, but transplanting this to behavio… 2026-09-01 published
From Local to Global: A Graph RAG Approach to Query-Focused Summarization taaft The use of retrieval-augmented generation (RAG) to retrieve relevant information from an external k… 2024-04-24 published
From Memorization to Absorption: Mixed-Policy RL for Continual Knowledge Injection taaft Continual knowledge injection is essential for keeping large language models up-to-date in a fast-e… 2026-08-26 published
From Nowcasting to Forecasting: Adapting a Reanalysis-Trained taaft Accurate cloud-cover forecasts are important for temperature prediction, radiation forecasting, and… 2026-09-03 published
From Prior-Guided Heuristics to Deployable Agents: Accelerating Demonstration-Driven Reinforcement Learning for Deadline-Constrained Network Control taaft Timely delivery of delay-sensitive information over dynamic, heterogeneous networks is essential fo… 2026-09-03 published
From Production Traffic to Post-Training: Building a Self-Hosted LLM That Covers the Corporate Request Mix taaft Data-residency constraints force enterprises to self-host LLMs, but continuous adoption of newer mo… 2026-09-01 published
From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning taaft In the realm of Large Language Models (LLMs), the balance between instruction data quality and quan… 2023-08-23 published
From Relaxed Indexability to Exact Indexability: A $t$-Step Approach for Partially Observable Restless Bandits taaft Whittle index policies offer a scalable method for restless multi-armed bandits, but under partial… 2026-08-25 published
From Reweighting to Rewriting: Unlocking the Intervention Effects of Influential Samples in Training Data Attribution taaft Training data attribution (TDA) aims to identify training examples that shape model behavior, but i… 2026-09-02 published
From Specialization to Generalization: Instruction-tuned LLMs for Robust Harmful Content Mitigation taaft Large language models (LLMs) demonstrate impressive performance across a wide range of general NLP… 2026-08-26 published
From Tokens to Semantics: Leveraging Complementary Signals for Hallucination Detection in Black-Box LLMs taaft When LLMs support public-facing or high-stakes workflows, missed fabrications can harm users and in… 2026-09-02 published
From topology learning to graph generation: A unifying perspective taaft Learning graph structures from data is a fundamental problem that spans a wide range of signal proc… 2026-09-02 published
From Truncation to Commitment: Persistent Context in Uniform Discrete Diffusion taaft Uniform-state discrete diffusion models update all tokens in parallel while keeping every position… 2026-09-01 published
From Verdict to Diagnosis: Attributable Security Review of Pull Requests taaft Automated code reviewers are increasingly used as gates on pull requests (PRs), yet evaluations mea… 2026-08-26 published
From Vision to Language: Investigating Causal Information Flow in Multimodal Decision-Making taaft Vision-Language Models are commonly evaluated through their final predictions, but understanding wh… 2026-09-04 published
From Visual Cues to Spoken Narration: Rethinking Audio Description taaft Audio Description (AD) provides spoken narration of visual events during dialogue gaps, making movi… 2026-09-01 published
From Zero to Hero: An Open LLM Ecosystem for Armenian taaft Pretraining data for Armenian, a morphologically rich and low-resource language, is scarce, and no… 2026-09-03 published
Frontier LLMs are effective batch optimizers: Assessing reasoning models in continuous and discrete settings taaft Frontier large language models (LLMs) have become attractive priors for optimization due to their l… 2026-09-02 published
FSGNet: A Frequency-Aware and Semantic Guidance Network for Infrared Small Target Detection taaft Infrared small target detection (IRSTD) aims to identify and distinguish small targets from complex… 2026-03-26 published
FU-Mamba: A Frequency-Enhanced Dynamic Scanning Framework for Oralscan Image Segmentation taaft Oralscan image segmentation is essential for computer-aided diagnosis and treatment planning in dig… 2026-08-27 published
FuDU: A Fuzzy Dual-dimensional Uncertainty Framework for Streaming Active Learning in Industrial Defect Detection taaft Ensuring the reliability of deep learning models in real-time industrial defect detection is critic… 2026-09-02 published
Full-Model Optimality for Tunable Linear Generative Priors in Compressed Sensing taaft Generative models have been studied experimentally and theoretically as priors for inverse problems… 2026-09-02 published
Full-Pipeline Inference Optimization for MiMo-V2.5 Series: Pushing Hybrid SWA Efficiency to the Limit taaft We present a full-pipeline inference optimization for the MiMo-V2.5 model family, which combines Hy… 2026-07-14 published
Fully Unleashing the Multimodal Attacker: Meta-Adaptive Jailbreaking of Vision-Language Models taaft The safety of large vision-language models is increasingly stress-tested by multimodal jailbreaks,… 2026-08-27 published
FuncRoom-Agent: Sequential Feed-Forward 3D Functional Indoor Scene Generation taaft We introduce Function-Room Generation, a new indoor 3D scene generation setting that creates rooms… 2026-08-30 published
Functional Degeneracy in Neural Networks: Measurement and Pruning taaft A central question in modern machine learning is how much a trained model can be compressed without… 2026-08-31 published
Functional linear regression from sparse to dense designs: a pooling-ridge method and minimax optimality taaft Functional data analysis is an important statistical field that treats data as random functions. In… 2026-08-26 published
FUSE: An Evaluating Framework for Dangerous Capabilities of LLMs taaft Fragmented safety evaluation undermines the governance of dangerous AI capabilities. We present a m… 2026-09-02 published
FUSED: Forensic-Semantic Mixture-of-Experts for AI Inpainting Detection and Localization taaft Diffusion-based inpainting models modify only a localized part of an image, while many AI-image det… 2026-08-28 published
Future-Interactions-Aware Trajectory Prediction via Braid Theory taaft To safely operate, an autonomous vehicle must know the future behavior of a potentially high number… 2026-03-23 published
FVeinSyn: Synthetic Finger Vein Image Generator taaft A major challenge in finger vein recognition is the lack of large-scale public datasets. Existing d… 2026-08-27 published