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

Distilling deep optical flow stereo methods to retrieve dense three-dimensional wind fields taaft Geostationary atmospheric motion vectors (AMVs) provide the dense horizontal wind vectors (u,v) and… 2026-09-02 published
Distilling Reasoning Capabilities into Smaller Language Models taaft Step-by-step reasoning approaches like chain of thought (CoT) have proved to be very effective in i… 2022-12-01 published
Distinguishing homolytic versus heterolytic bond dissociation of phenyl sulfonium cations with localized active space methods IBM Modeling chemical reactions with quantum chemical methods is challenging when the electronic struct… 2024-04-22 published
Distortion Audio Effects: Learning How to Recover the Clean Signal taaft Given the recent advances in music source separation and automatic mixing, removing audio effects i… 2022-02-03 published
Distributed Implicit Harm: A Compositional Safety Blind Spot in MLLM-Based Video Moderation taaft Despite their growing use in video moderation, multimodal large language models (MLLMs) exhibit a c… 2026-08-31 published
DK-GBMKKM: Dynamic Kernel-Space Granular-Ball Multiple Kernel $k$-Means Clustering taaft Multiple kernel $k$-means integrates complementary nonlinear similarities by learning a combination… 2026-09-01 published
DKL: Decoupled Knowledge Learning for Instruction-Tuned Language Models taaft RAG has become the de facto method for incorporating new, corpus-specific knowledge into an instruc… 2026-09-02 published
DMRL: Document-Mediated Reinforcement Learning for Skill Optimization in Advertising Recommendation taaft Advertising recommendation requires continuously tuning complex system parameters while balancing c… 2026-09-02 published
DNC-IMM: Early Lane-Change Intention Recognition via Neural Calibration Based on Driving Context Information taaft Early recognition of lane-change intention is essential for proactive decision-making in autonomous… 2026-09-01 published
Do As I Can, Not As I Say: Grounding Language in Robotic Affordances Google Large language models can encode a wealth of semantic knowledge about the world. Such knowledge cou… 2022-04-04 published
Do Better Imagined Rollouts Mean Better Robot Control? A Controlled Study of World-Model Evaluation Under Feedback taaft Predictive models are increasingly used in robotics for state estimation, planning, control, and po… 2026-09-02 published
Do Cantonese-Adapted Language Models Better Predict Cantonese Reading? A Cross-Model Eye-Tracking Evaluation taaft Information-theoretic measures derived from autoregressive language models are widely used to chara… 2026-09-02 published
Do General NLP Embeddings Capture Ontological Reasoning? taaft General-purpose NLP embedding models perform well on linguistic tasks, but their ability to capture… 2026-08-31 published
Do GUI Agents Know When Not to Act? Enabling Conflict-Aware Termination for Multimodal GUI Agents taaft Graphical user interface (GUI) agents are increasingly used to execute natural-language instruction… 2026-09-03 published
Do Large Language Models Capture the Diversity in their Training Data? taaft Large language models are trained to model conditional distributions over text, yet it remains inad… 2026-09-02 published
Do Large Language Models Reduce Research Novelty? Evidence from Information Systems Journals taaft Large language models are increasingly used in scholarly work, yet it remains unclear whether their… 2026-03-23 published
Do LLMs Change Their Minds Like Humans? Diagnosing Human--LLM Divergence in Single-Turn Persuasion Judgments taaft Large language models (LLMs) are increasingly deployed as proxies for human participants in social… 2026-08-30 published
Do LLMs Exhibit Coherent Knowledge Structures in Mathematical Reasoning? A Perspective from Knowledge Space Theory taaft Human knowledge is inherently structured and interdependent: mastery of a concept requires prior ma… 2026-09-04 published
Do Recipes Have Personas? Characterizing and Generating Creator Style in Attributed Procedural Graphs taaft While large language models (LLMs) possess vast zero-shot procedural knowledge, their tendency to p… 2026-08-25 published
Do Tabular Foundation Models Know Physics? Contamination, Units, and the Deterministic Limit taaft Tabular foundation models (TFMs) learn to fill in tables the way language models fill in text, and… 2026-09-02 published
Do Video Generators Track the World Across Segments? A Benchmark and Method for World-State Reasoning in Video Continuation taaft Video generators build long videos by composing shorter parts, either by generating segments one af… 2026-09-03 published
Do Vision-Language Models Agree on the Affective Qualities of Shape? A Cross-Model Audit for Generative Design Interfaces taaft Generative design interfaces increasingly expose semantic controls that let users steer output with… 2026-08-26 published
Doc-REFRAG: Rethinking Multimodal Document Retrieval-Augmented Generation taaft Real-world knowledge resides in multimodal documents, necessitating retrieval-augmented generation… 2026-08-31 published
DocHop: Benchmarking Out-of-domain Multi-hop Reasoning in Information-Dense Documents taaft Multimodal Large Language Models (MLLMs) have achieved strong performance on structured visual unde… 2026-09-02 published
DocPedia: Unleashing the Power of Large Multimodal Model in the Frequency Domain for Versatile Document Understanding taaft This work presents DocPedia, a novel large multimodal model (LMM) for versatile OCR-free document u… 2023-11-20 published
DocTalkBN: A Novel Dataset of Expert Telemedicine Conversations in Bengali taaft Reliable medical conversational AI requires authentic expert--patient interaction data, yet such da… 2026-08-27 published
Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus taaft Large language models have led to remarkable progress on many NLP tasks, and researchers are turnin… 2021-04-18 published
DODR: Deterministic Operator-Driven Reasoning in Latent Space taaft Autoregressive (AR) large language models formulate reasoning as token-level probabilistic sampling… 2026-09-04 published
Does Episodic Memory Help Close the Lexical Frequency Gap in Sensitivity to Syntactic Contrasts? A Test Using Retrieval-Augmented Language Models taaft Grammatical knowledge and how it is empirically tested are typically considered robust to the frequ… 2026-08-24 published
Does Imitation Learning Preserve Temporal Robustness in Dexterous Manipulation? An Expert-Learner Comparison Across Task Execution Speeds taaft Dexterous manipulation policies learned by imitation are typically evaluated for robustness to vari… 2026-09-01 published
Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement taaft On-policy distillation (OPD) offers dense token-level supervision as an alternative to the sparse o… 2026-08-31 published
Does Playing it Safe Count as Faithfulness? Reassessing LVLM Hallucination Mitigation Methods taaft Recent inference-time hallucination mitigation methods for large vision-language models (LVLMs) rep… 2026-09-01 published
Does Reasoning Mitigate Backdoor Attacks? A Neuro-Symbolic Perspective taaft Neuro-Symbolic (NeSy) AI has recently emerged as a novel paradigm to enable trustworthy AI, aiming… 2026-08-31 published
Does task decomposition improve automatic NLG evaluation? taaft The LLM-as-a-judge (LLMaJ) framework has emerged as a promising solution for cheap, reproducible, r… 2026-09-01 published
Does the Selected Object Reach the Reader? Auditing Identity Handoffs in Grounded Language-Model Pipelines taaft Grounded language-model pipelines can be divided into three stages: selecting an object, retrieving… 2026-09-04 published
Does This Gradient Spark Joy? Google DeepMind Policy gradient computes a backward pass for every sample, even though the backward pass is expensi… 2026-03-20 published