💬 LLMs - Bingran

🖥️ML Systems Academic

arxiv.org·

A retrieval conditioned rebinding circuit for dynamic entity tracking in large language models

🔄Transformers Academic

arxiv.org·

ActiveMimic: Egocentric Video Pretraining with Active Perception

⚙️Model Training Academic

arxiv.org·

PermDoRA -- Understanding Adapter Interference in Language Models: Limits of Parameter-Space Geometry

🔄Transformers Academic

arxiv.org·

MechLens: Late Crystallization of Factual Knowledge Explains Intervention Effectiveness in Language Models

🧠AI Research Academic

arxiv.org·

ViP-VL: Vietnamese Self-supervised Speech Pretraining Model with Vector-Quantization Learning

⚙️Model Training Academic

arxiv.org·

Cross Paraphrastic Invariance Learning for Hallucination Detection

⚙️Model Training Academic

arxiv.org·

Domain-Adapted Small Language Models with Hybrid Post-Processing: Achieving Cost-Efficient, Low-Latency Multi-Label Structured Prediction via LoRA Fine-Tuning on Scarce Data

⚙️Model Training Academic

arxiv.org·

SPADE: Split-and-Delay Embeddings for Autoregressive High-Granularity Calorimeter Simulation

🧠AI Research Academic

arxiv.org·

Shared Latent Structures Enable Unified Backdoor Detection and Mitigation in LLMs

🔍Interpretability Academic

arxiv.org·

Improving Cross-Lingual Factual Recall via Consistency-Driven Reinforcement Learning

⚙️Model Training Academic

arxiv.org·

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

🧠AI Research Academic

arxiv.org·

The Amplifying Mirror: Locating and Steering the Partisan Direction inside a Large Language Model

🔍Interpretability Academic

arxiv.org·

Multilingual Sentiment Aware Text Summarization A Reinforcement Learning Approach for Consistency Maintenance

🎮Reinforcement Learning Academic

arxiv.org·

SpikeDecoder: Realizing the GPT Architecture with Spiking Neural Networks

🔄Transformers Academic

arxiv.org·

Small Experiments, Cheaper Decisions: A Case Study in Staged Promotion for Micro-Pretraining

Hallucination Cascade: Analyzing Error Propagation in Multi-Agent LLM Systems

Corpus Augmentation for Sign Language Translation via LLM-Guided Video Stitching

Data-Constrained Language Model Pretraining: Improved Regularization and Scaling Laws

Multi-Hop Knowledge Composition is Bound by Pretraining Exposure

Making Locality-aware GEMM Compatible with Page-Granularity Placement on Chiplet GPUs

A retrieval conditioned rebinding circuit for dynamic entity tracking in large language models

ActiveMimic: Egocentric Video Pretraining with Active Perception

PermDoRA -- Understanding Adapter Interference in Language Models: Limits of Parameter-Space Geometry

MechLens: Late Crystallization of Factual Knowledge Explains Intervention Effectiveness in Language Models

ViP-VL: Vietnamese Self-supervised Speech Pretraining Model with Vector-Quantization Learning

Cross Paraphrastic Invariance Learning for Hallucination Detection

Domain-Adapted Small Language Models with Hybrid Post-Processing: Achieving Cost-Efficient, Low-Latency Multi-Label Structured Prediction via LoRA Fine-Tuning on Scarce Data

SPADE: Split-and-Delay Embeddings for Autoregressive High-Granularity Calorimeter Simulation

Shared Latent Structures Enable Unified Backdoor Detection and Mitigation in LLMs

Improving Cross-Lingual Factual Recall via Consistency-Driven Reinforcement Learning

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

The Amplifying Mirror: Locating and Steering the Partisan Direction inside a Large Language Model

Multilingual Sentiment Aware Text Summarization A Reinforcement Learning Approach for Consistency Maintenance

SpikeDecoder: Realizing the GPT Architecture with Spiking Neural Networks