Semantic consensus on model outputs for public prompts enables federated LLM fine-tuning that matches parameter-aggregation baselines with orders-of-magnitude lower communication.
See https://vicuna
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
Chain-based Distillation constructs a sequence of anchor models to enable efficient initialization of variable-sized SLMs through interpolation, with bridge distillation for cross-architecture transfer, yielding better performance than scratch training.
DR-Smoothing introduces a disrupt-then-rectify prompt processing scheme into smoothing defenses, delivering tight theoretical bounds on success probability against both token- and prompt-level jailbreaks.
Sync-R1 applies cooperative RL with Sync-GRPO and Dynamic Group Scaling to achieve superior cross-task personalized reasoning in multimodal models on the new UnifyBench++ dataset.
LBLLM achieves better accuracy than prior binarization methods for LLMs by decoupling weight and activation quantization through initialization, layer-wise distillation, and learnable activation scaling.
citing papers explorer
-
Beyond Parameter Aggregation: Semantic Consensus for Federated Fine-Tuning of LLMs
Semantic consensus on model outputs for public prompts enables federated LLM fine-tuning that matches parameter-aggregation baselines with orders-of-magnitude lower communication.
-
Chain-based Distillation for Effective Initialization of Variable-Sized Small Language Models
Chain-based Distillation constructs a sequence of anchor models to enable efficient initialization of variable-sized SLMs through interpolation, with bridge distillation for cross-architecture transfer, yielding better performance than scratch training.
-
Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing
DR-Smoothing introduces a disrupt-then-rectify prompt processing scheme into smoothing defenses, delivering tight theoretical bounds on success probability against both token- and prompt-level jailbreaks.
-
Uni-Synergy: Bridging Understanding and Generation for Personalized Reasoning via Co-operative Reinforcement Learning
Sync-R1 applies cooperative RL with Sync-GRPO and Dynamic Group Scaling to achieve superior cross-task personalized reasoning in multimodal models on the new UnifyBench++ dataset.
-
LBLLM: Lightweight Binarization of Large Language Models via Three-Stage Distillation
LBLLM achieves better accuracy than prior binarization methods for LLMs by decoupling weight and activation quantization through initialization, layer-wise distillation, and learnable activation scaling.