Cs-Cl
Think-Augmented Function Calling: Improving LLM Parameter Accuracy Through Embedded Reasoning
FlashBlock: Attention Caching for Efficient Long-Context Block Diffusion
A Human-in-the-Loop, LLM-Centered Architecture for Knowledge-Graph Question Answering
Causal Front-Door Adjustment for Robust Jailbreak Attacks on LLMs
AgentXRay: White-Boxing Agentic Systems via Workflow Reconstruction
AFD-INSTRUCTION: A Comprehensive Antibody Instruction Dataset with Functional Annotations for LLM-Based Understanding and Design
Recontextualizing Famous Quotes for Brand Slogan Generation
PersonaPlex: Voice and Role Control for Full Duplex Conversational Speech Models
Quantifying and Attributing Polarization to Annotator Groups
PACE: Defying the Scaling Hypothesis of Exploration in Iterative Alignment for Mathematical Reasoning
Benchmarking Automatic Speech Recognition for Indian Languages in Agricultural Contexts
Simulated Adoption: Decoupling Magnitude and Direction in LLM In-Context Conflict Resolution
OmniCode: A Benchmark for Evaluating Software Engineering Agents
Analyzing Diffusion and Autoregressive Vision Language Models in Multimodal Embedding Space
Back to Basics: Revisiting Exploration in Reinforcement Learning for LLM Reasoning via Generative Probabilities
Relevance-aware Multi-context Contrastive Decoding for Retrieval-augmented Visual Question Answering
SAGE: Benchmarking and Improving Retrieval for Deep Research Agents
WAFFLE: Finetuning Multi-Modal Models for Automated Front-End Development
Not All Layers Need Tuning: Selective Layer Restoration Recovers Diversity
Learning a Generative Meta-Model of LLM Activations
DAWN: Dependency-Aware Fast Inference for Diffusion LLMs
Instructional Text Across Disciplines: A Survey of Representations, Downstream Tasks, and Open Challenges Toward Capable AI Agents
