🧠 AI Research - Bingran · Scour

Metadata-Aware Multi-Prompt Reasoning for Zero-Shot Accident Understanding

🤖AI Agents Academic

Minibatch Selection via Partition Matroid Constrained Gradient Matching

⚙️Model Training Academic

Towards Tight Bounds for Streaming Attention

🔄Transformers Academic

Fourier Features Let Agents Learn High Precision Policies with Imitation Learning

🎮Reinforcement Learning Academic

Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?

⚙️Model Training Academic

Building Social World Models with Large Language Models

💬LLMs Academic

GITCO: Gated Inference-Time Context Optimization in TSFMs

💬LLMs Academic

The Easy, the Hard, and the Learnable: Confidence and Difficulty-Adaptive Policy Optimization for LLM Reasoning

🎮Reinforcement Learning Academic

A Controlled Study of Decoding-Time Truthfulness Methods on Instruction-Tuned LLMs

💬LLMs Academic

Preserving Plasticity in Continual Learning via Dynamical Isometry

🎮Reinforcement Learning Academic

Neuron-based Personality Trait Induction in Large Language Models

💬LLMs Academic

Attention Consistent Longitudinal Medical Visual Question Answering Guided by Vision Foundation Models

🔄Transformers Academic

What Uncertainties Do We Need for Dynamical Systems?

📐Scaling Laws Academic

Multi-View Speech Representation Learning for Parkinson's Disease Detection Using Context-guided Cross-modal Attention

💬LLMs Academic

GRAMformer: Any-Order Modality Interactions via Volumetric Multimodal Cross-Attention

🔄Transformers Academic

SwarmSense-DNN: A Trustworthy and Decentralized Neural Framework for Proactive Anomaly Defense in Consumer IoT

🤖AI Agents Academic

Voting Protocols as Coordination Mechanisms for Role-Constrained Multi-Agent Tutoring Systems

🎮Reinforcement Learning Academic

LifeSentence: Language models can encode human life course trajectories from longitudinal panel data

🔄Transformers Academic

Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models

💬LLMs Academic

SWE-InfraBench: Evaluating Language Models on Cloud Infrastructure Code

💬LLMs Academic

Log in to enable infinite scrolling