Entities · Models
Qwen2.5
16 articles tagged with this entity.
-
Teacher Supervision over Representation Equivalence Classes
-
Transplanting, inverting, and preventing a misalignment persona: method-conditional emergent misalignment in Qwen2.5
-
Beyond Entropy: Learning from Token-Level Distributional Deviations for LLM Reasoning
-
The Reservoir Attention Network: Cross-Pass State in Pretrained Transformers via Content-Addressable Reservoir Injection
-
The Quality-Utility Paradox: Why High-Reward Data Impairs Small Model Mathematical Reasoning
-
Minibatch Selection via Partition Matroid Constrained Gradient Matching
-
Trajectory Geometry of Transformer Representations Across Layers
-
TARPO: Token-Wise Latent-Explicit Reasoning via Action-Routing Policy Optimization
-
ProjQ: Project-and-Quantize for Adapter-Aware LLM Compression
-
Med-HEAL: Analyzing and Mitigating Hallucinations in Medical LLMs with Hallucination-Aware In-Context Learning
-
Learning to Predict Future-Aligned Research Proposals with Language Models
-
Shipping a Trillion Parameters With a Hub Bucket: Delta Weight Sync in TRL
-
DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning
-
Judge Circuits
-
Quantifying Empirical Compute-Supervision Tradeoffs in RLVR
-
Harmful Intent as a Geometrically Recoverable Feature of LLM Residual Streams