Entities · Models
Qwen2.5-7B
30 articles tagged with this entity.
-
A Retrieval-Augmented Framework for Detecting and Resolving Pragmatic Ambiguities in Natural Language Requirements
-
ProbeLogits: Kernel-Level LLM Inference Primitives for AI-Native Operating Systems
-
Robust for the Wrong Reasons: The Representational Geometry of LLM Robustness to Science Skepticism
-
Knowledge Distillation from Large Reasoning Models to Compact Student Models: A Case Study on the John O Bryan Mathematics Competition
-
Adaptive Evaluation of Out-of-Band Defenses Against Prompt Injection in LLM Agents
-
SharQ: Bridging Activation Sparsity and FP4 Quantization for LLM Inference
-
Reasoning Quality Emerges Early: Data Curation for Reasoning Models
-
Improved Large Language Diffusion Models
-
Rift: A Conflict Signature for Deception in Language Models
-
SpectrumKV: Per-Token Mixed-Precision KV Cache Transfer for Prefill-Decode Disaggregated LLM Serving
-
Answer Presence Drives RAG Rewriting Gains
-
When Denser Credit Is Not Enough: Evidence-Calibrated Policy Optimization for Long-Horizon LLM Agent Training
-
Efficient Reasoning on the Edge
-
CARE-RL: Capability-Aware Reinforcement Learning for Mitigating Cross-Domain Conflicts
-
HypothesisMed: Inference-Time Answer Fusion and Structured Hypothesis-Space Reporting for Biomedical Question Answering
-
DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning
-
Low-Resource Safety Failures Are Action Failures, Not Representation Failures
-
Adapting Large Language Models to a Low-Resource Agglutinative Language: A Comparative Study of LoRA and QLoRA for Bashkir
-
Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning
-
On the Construction and Implications of Low-Loss Valleys in LoRA-based Bayesian Inference
-
DeepTool: Scaling Interleaved Deliberation in Tool-Integrated Reasoning via Process-Supervised Reinforcement Learning
-
Hurwitz Quaternion Multiplicative Quantization for KV Cache Compression
-
Copy-as-Decode: Grammar-Constrained Parallel Prefill for LLM Editing
-
The Model Parking Tax: Quantifying the Hidden Energy Cost of Always-On GPU Model Deployment
-
F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare
-
What Makes a Medical Checker Trainable? Diagnosing Signal Collapse and Reward Hacking in Checker-Guided RAG for Biomedical QA
-
Learning Faster with Better Tokens: Parameter-Efficient Vocabulary Adaptation for Specialized Text Summarization
-
Energy-Regularized Sequential Model Editing on Hyperspheres
-
The Realignment Problem: When Right becomes Wrong in LLMs
-
MemRouter: Memory-as-Embedding Routing for Long-Term Conversational Agents