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

Trace as State: Reasoning Traces as Conditional States for Long-Context Transformers taaft Transformers process information causally, but long-context reasoning may depend on task state disc… 2026-09-02 published
TRACE-CRC: Trajectory-Adaptive Conformal Risk Control for Multi-Step Channel State Information Prediction taaft Reliable prediction of time-varying channel state information (CSI) is essential for efficient wire… 2026-08-27 published
TRACE: Object Motion Editing in Videos with First-Frame Trajectory Guidance taaft We study object motion path editing in videos, where the goal is to alter a target object's traject… 2026-03-26 published
TRACE: Trajectory Recovery with State Propagation Diffusion for Urban Mobility taaft High-quality GPS trajectories are essential for location-based web services and smart city applicat… 2026-03-19 published
Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills taaft Large Language Model (LLM) agents increasingly rely on domain-specific skills, yet manually authori… 2026-03-26 published
Trace2Tower: Transition-Aware EigenTrace Induction of Multi-Level Skills for LLM Agents taaft Large language model agents increasingly rely on execution traces to master complex interactive tas… 2026-09-04 published
Tracing Generated Samples to Training-Data Clusters in Flow-Matching Models taaft Understanding which training samples influence a generated image is an important problem in generat… 2026-08-30 published
Train What You Deploy: Closing the MLP Reachability Gap in Low-Rank Clone Distillation taaft A compressed student has two shapes that need not agree: the weight it deploys at inference and the… 2026-09-02 published
Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback Anthropic We apply preference modeling and reinforcement learning from human feedback (RLHF) to finetune lang… 2022-04-12 published
Training a Tokenizer for Free with Private Federated Learning Apple Federated learning with differential privacy, i.e. private federated learning (PFL), makes it possi… 2022-03-15 published
Training Communication-Efficient Mixture-of-Experts Language Models with Layer Re-Configuration taaft When training Mixture-of-Experts (MoE) language models with expert parallelism, all-to-all token di… 2026-08-28 published
Training Compute-Optimal Large Language Models Google DeepMind We investigate the optimal model size and number of tokens for training a transformer language mode… 2022-03-29 published
Training Language Models to Follow Instructions with Human Feedback OpenAI Making language models bigger does not inherently make them better at following a user's intent. Fo… 2022-03-04 published
Training Large Language Models for Small-Molecule Design with Synthetic Task Scaling taaft Designing viable drug candidates requires searching a combinatorially large and rugged chemical spa… 2026-09-04 published
Training neural networks with end-to-end optical backpropagation taaft Optics is an exciting route for the next generation of computing hardware for machine learning, pro… 2023-08-09 published
Training seeds and model-selection stability in recommender-system evaluation taaft Recommender-system experiments often rely on a single random training seed, assuming that run-to-ru… 2026-09-02 published
Training Verifiers to Solve Math Word Problems OpenAI State-of-the-art language models can match human performance on many tasks, but they still struggle… 2021-10-27 published
Training-Free Halving of Activated Experts in Fine-Grained Mixture-of-Experts Models taaft Modern fine-grained Mixture-of-Experts (MoE) models route each token to a small number of experts a… 2026-09-04 published
Training-Free Logical and Structural Anomaly Detection via Calibrated Fusion taaft Industrial anomaly detection must handle two distinct defect families: structural anomalies, which… 2026-09-04 published
Training-free Suction Grasp Detection for Deformed Aseptic Cartons Using Vision-Language Models and Geometric Surface Scoring taaft Robotic sorting of recyclable waste is challenging due to the deformable and geometrically inconsis… 2026-08-28 published
Training-Free Temporal Abstraction for General Video Understanding taaft Videos are expensive to analyze frame by frame, yet many video understanding tasks depend on knowin… 2026-08-28 published
Trajectory-Optimized Time Reparameterization for Learning-Compatible Reduced-Order Modeling of Stiff Dynamical Systems Tavus Stiff dynamical systems present a challenge for machine-learning reduced-order models (ML-ROMs), as… 2026-03-17 published
TrajLoom: Dense Future Trajectory Generation from Video taaft Predicting future motion is crucial in video understanding and controllable video generation. Dense… 2026-03-23 published
TrajMind: Chaining Role-Specialized LoRAs for Fast-and-Slow Collective Trajectory Anomaly Diagnosis taaft Diagnosing collective anomalies from urban trajectories is increasingly important for traffic gover… 2026-09-02 published
TransAct: Transformer-based Realtime User Action Model for Recommendation at Pinterest Pinterest Sequential models that encode user activity for next action prediction have become a popular design… 2023-05-31 published
Transfer Learning for Contextual Joint Assortment-Pricing under Cross-Market Heterogeneity taaft We study transfer learning for contextual joint assortment-pricing under a multinomial logit choice… 2026-03-18 published
Transfer Safety Awareness for Cross-Modal Safety Drift in Multimodal Large Language Models taaft Visual modality enhances the capabilities of multimodal large language models (MLLMs) but also intr… 2026-09-02 published
Transfiver: Human-AI Co-Inference through a Shared Editable State taaft Long-term human-AI interaction is difficult because the information that guides inference is update… 2026-09-03 published
TransPhy: Visual In-Context Learning for Physically Grounded Image Editing taaft Visual demonstrations provide a natural interface for specifying image transformations that are dif… 2026-08-25 published
TransRetrieval: Scaling Up Transformer-Based Retrieval for Industrial Recommendation taaft Applying scaling laws to recommendation retrieval is hindered by feature heterogeneity: naively sta… 2026-08-26 published
TraveL: Transformer-based Multi-view Path Distributional Representation Learning taaft Path representation learning (PRL) for road networks has received increasing research attention, du… 2026-09-03 published
Tree-of-Ideas: Automated Research Ideation via Cross-Trajectory Reasoning over Scholarly Evolution taaft Effective research ideation requires moving beyond a static understanding of prior work to trace ho… 2026-08-11 published
TreeFI: Value-Aware Statistical Fault Injection for Deep Neural Networks taaft Reliability evaluation of deep neural networks under hardware faults commonly relies on fault injec… 2026-09-04 published
TREX: Trajectory Explanations for Multi-Objective Reinforcement Learning taaft Reinforcement Learning (RL) has demonstrated its ability to solve complex decision-making problems… 2026-03-23 published
TRIAGE: Three-level Routing and Intelligent Agent Guidance for Efficient Execution taaft Large Language Model (LLM) agents based on the ReAct paradigm have demonstrated remarkable capabili… 2026-09-01 published
TRINITY: A Multi-Perspective Benchmark for Personal-Style Video Highlight Detection taaft Traditional video highlight detection relies on a narrow, event-centric definition of saliency, whi… 2026-08-30 published