🧠 LLMs - cwensel

⚙️MLOps Academic

arxiv.org·

TLRD: Teaching LLMs to Reason over Tabular Data with Tri-Level Rationale Distillation

🔗LLM Workflows Academic

arxiv.org·

SigmaScale: LLM Compression with SVD-based Low-Rank Decomposition and Learned Scaling Matrices

🔢Vector Databases Academic

arxiv.org·

LLMCodec: Adapting Video Codecs for Efficient Weight Compression of Large Language Models

⚙️MLOps Academic

arxiv.org·

Streaming Interventions: Can Video Large Language Models Correct Mistakes as They Occur?

⚙️MLOps Academic

arxiv.org·

Improving Answer Extraction in Context-based Question Answering Systems Using LLMs

📚RAG Academic

arxiv.org·

RASFT: Rollout-Adaptive Supervised Fine-Tuning for Reasoning

⚙️MLOps Academic

arxiv.org·

MemToolAgent overview with a simple restaurant booking scenario where the agent retrieves similar memories, receives feedback on an invalid time format, and generates a reflection to update its memory

🕵️AI Agents Academic

arxiv.org·

Sequential Data Poisoning in LLM Post-Training

⚙️MLOps Academic

arxiv.org·

Stress-testing medical large language models reveals latent safety pathology beyond benchmark accuracy

⚙️MLOps Academic

arxiv.org·

YouZhi: Towards High-Concurrency Financial LLMs via Adaptive GQA-to-MLA Transition

🔢Vector Databases Academic

arxiv.org·

LongRTL: Graph-Similarity-Guided LLM-driven Long Context RTL Optimization

📚RAG Academic

arxiv.org·

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

⚙️MLOps Academic

arxiv.org·

Reasoning Shift: How Context Silently Shortens LLM Reasoning

⚙️MLOps Academic

arxiv.org·

Closing the Prior-Posterior Loop: Self-Reflective Molecular Design with Analysis-Driven LLM Iteration

📚RAG Academic

arxiv.org·

Uncertainty-Aware LLM-Guided Policy Shaping for Sparse-Reward Reinforcement Learning

🔗LLM Workflows Academic

arxiv.org·

PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models

From Symbolic to Geometric: Enabling Spatial Reasoning in Large Language Models

Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating

When LLMs Invent Rust Crates: An Empirical Study of Hallucination Patterns and Mitigation

CASS-RTL: Correctness-Aware Subspace Steering for RTL Generation with LLMs

TLRD: Teaching LLMs to Reason over Tabular Data with Tri-Level Rationale Distillation

SigmaScale: LLM Compression with SVD-based Low-Rank Decomposition and Learned Scaling Matrices

LLMCodec: Adapting Video Codecs for Efficient Weight Compression of Large Language Models

Streaming Interventions: Can Video Large Language Models Correct Mistakes as They Occur?

Improving Answer Extraction in Context-based Question Answering Systems Using LLMs

RASFT: Rollout-Adaptive Supervised Fine-Tuning for Reasoning

MemToolAgent overview with a simple restaurant booking scenario where the agent retrieves similar memories, receives feedback on an invalid time format, and generates a reflection to update its memory

Sequential Data Poisoning in LLM Post-Training

Stress-testing medical large language models reveals latent safety pathology beyond benchmark accuracy

YouZhi: Towards High-Concurrency Financial LLMs via Adaptive GQA-to-MLA Transition

LongRTL: Graph-Similarity-Guided LLM-driven Long Context RTL Optimization

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

Reasoning Shift: How Context Silently Shortens LLM Reasoning

Closing the Prior-Posterior Loop: Self-Reflective Molecular Design with Analysis-Driven LLM Iteration

Uncertainty-Aware LLM-Guided Policy Shaping for Sparse-Reward Reinforcement Learning