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

Enhancing Multimodal Emotion Recognition via Multi-Feature Encoding and Attention-Based Fusion taaft Multimodal emotion recognition has attracted growing interest due to its importance in human-comput… 2026-09-04 published
Enhancing Pretrained Model-based Continual Representation Learning via Guided Random Projection taaft Recent paradigms in Random Projection Layer (RPL)-based continual representation learning have demo… 2026-03-19 published
Enoki: Efficient Multi-Level Hallucination Detection taaft Ensuring factuality remains a critical challenge for deploying LLMs in high-stakes settings. Existi… 2026-09-01 published
Entangled Representations Amplify Collateral Damage in Unlearning taaft A long-held intuition in interpretability research is that representational entanglement, the shari… 2026-09-02 published
Entanglement as Memory: Mechanistic Interpretability of Quantum Language Models taaft Quantum language models have shown competitive performance on sequential tasks, yet whether trained… 2026-03-27 published
Entity Matching using Large Language Models taaft Entity matching is the task of deciding whether two entity descriptions refer to the same real-worl… 2023-10-17 published
Entity-Memory Graph Retrieval Improves Evidence Coverage in Long-Conversation Question Answering taaft Entity-Memory graph retrieval keeps dialogue turns as verbatim Memory nodes, links repeated mention… 2026-08-28 published
ENTLORE: A Graph-Grounded Benchmark for Latent Organizational Reasoning in Enterprise Question Answering taaft Enterprise question answering is framed as retrieving internal documents and generating grounded an… 2026-08-11 published
Entropy trajectory shape predicts LLM reasoning reliability: A diagnostic study of uncertainty dynamics in chain-of-thought taaft Understanding uncertainty in chain-of-thought reasoning is critical for reliable deployment of larg… 2026-03-19 published
Environment Evolution for Terminal Agents taaft Scaling interactive and verifiable environments is critical for training terminal agents. As fronti… 2026-09-03 published
Epistemic Sybil Resistance: Multiplying AI Agents Without Multiplying Evidence taaft Multi-agent AI systems improve inference by spawning agents and synthesizing reports. But another a… 2026-09-01 published
Epistemic Warrant for LLM Recommendations: Characterizing the Basis for Reliance When Ground Truth Is Unavailable taaft Large language models are increasingly used to support organizational decisions, yet users often la… 2026-09-03 published
Equation Recast for Canonical Operator Learning Across Parametric PDEs taaft Learning solution operators across broad parameter ranges can require substantial coverage of both… 2026-09-02 published
Equivariant Covariance Tensors: Guaranteed SPD Uncertainty for Tensor-Valued Geometric Learning taaft Tensor-valued prediction is fundamental to geometric deep learning, yet uncertainty quantification… 2026-08-25 published
ERAGent: Enhancing Retrieval-Augmented Language Models with Improved Accuracy, Efficiency, and Personalization taaft Retrieval-augmented generation (RAG) for language models significantly improves language understand… 2024-05-06 published
EraseSAE: Surgical Concept Erasure in Text-to-Video Diffusion Models via Sparse Autoencoders taaft Recent advances in text-to-video (T2V) diffusion models have demonstrated remarkable generative cap… 2026-09-03 published
ERPBench: Evaluating LLM Agents for Enterprise Decision-Making Across Competitive Market Ecologies taaft Large language model (LLM) agents are increasingly proposed for enterprise workflows, yet existing… 2026-09-04 published
Ethio-ASR: Joint Multilingual Speech Recognition and Language Identification for Ethiopian Languages taaft We present Ethio-ASR, a suite of multilingual CTC-based automatic speech recognition (ASR) models j… 2026-03-24 published
Eureka: Human-Level Reward Design via Coding Large Language Models NVIDIA Large Language Models (LLMs) have excelled as high-level semantic planners for sequential decision-… 2023-10-19 published
EuroAlpaca: Task-Preserving Localisation of Instruction Data for European Languages taaft Machine translation (MT) offers a scalable way to extend English instruction-tuning data to multipl… 2026-09-04 published
Evaluating Deep Neural Networks Trained on Clinical Images in Dermatology with the Fitzpatrick 17k Dataset taaft How does the accuracy of deep neural network models trained to classify clinical images of skin con… 2021-04-20 published
Evaluating Discourse Phenomena in Neural Machine Translation Apple For machine translation to tackle discourse phenomena, models must have access to extra-sentential… 2017-11-01 published
Evaluating Graph Neural Networks for Change-Criticality Classification in Maritime Navigation Charts taaft Graph neural networks (GNNs) are a class of neural networks suitable for learning on graph-structur… 2026-09-02 published
Evaluating Language Models on Cross-Language Code Functional Equivalence taaft Background: Large Language Models (LLMs) have demonstrated strong performance across a variety of c… 2026-08-25 published
Evaluating Large Language Models Trained on Code taaft We introduce Codex, a GPT language model fine-tuned on publicly available code from GitHub, and stu… 2021-07-07 published
Evaluating LLMs on Conversational Text-to-SQL under Chain Ambiguity and Intent Drift taaft Recent advances in large language models (LLMs) have established conversational text-to-SQL as a pr… 2026-08-30 published
Evaluating Model-Free Policy Optimization in Masked-Action Environments via an Exact Blackjack Oracle taaft Infinite-shoe casino blackjack provides a rigorous, exactly verifiable benchmark for discrete stoch… 2026-03-19 published
Evaluating Multimodal LLMs as Generalist Vision-Language-Action Agents for Drone Control: Commanding, Approaching, Tracking and Searching taaft Multimodal Large Language Models (MLLMs) are strong perceivers of images and video. We ask how far… 2026-09-01 published
Evaluating Object Hallucination in Large Vision-Language Models Meituan Inspired by the superior language abilities of large language models (LLM), large vision-language m… 2023-05-17 published
Evaluating Skills, Not Just Agents: Agentic Continuous Evaluation of Skills taaft Enterprise agent programs are moving from prototypes into production, where reusable skills, tools,… 2026-08-20 published
Evaluating the Reliability and Fidelity of Automated Judgment Systems of Large Language Models taaft A Large Language Model (LLM) as judge evaluates the quality of victim Machine Learning (ML) models,… 2026-03-23 published
Evaluating Vision Foundation Models for Pixel and Object Classification in Microscopy taaft Deep learning underlies most modern approaches and tools in computer vision, including biomedical i… 2026-03-20 published
Event-triggered Control and Online Learning for Networked Systems under Computational Delays taaft Online learning-based control is a promising approach to control uncertain systems, where unknown c… 2026-08-30 published
Every Coin Has Two Sides: On the Dual Nature of Generalization in On-Policy Distillation of Large Language Models taaft On-policy distillation (OPD) transfers teacher capabilities by supervising trajectories sampled fro… 2026-08-17 published
Everyone assumes bigger AI models win. We built a 34,000-parameter earthquake detector that beats a model 8× its size. Transformer Lab Builds a compact seismic phase picker (33,610 parameters) that beats PhaseNet (268,443 parameters)… Transformer Lab
Evidence for Shared Routing Geometry and Dynamics in Sparse Mixture-of-Experts taaft Sparse mixture-of-experts (MoE) models use an independently parameterized router at each sparse lay… 2026-09-02 published