Fine-tuning neural PDE operators to regime endpoints reveals a physical direction in weight space that CCM uses to compose accurate merged models for new or extrapolated regimes from metadata or short prefixes.
Adamerging: Adaptive model merging for multi-task learning
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Merging breaks MoE routing via softmax sensitivity; HARC uses Hessian curvature for closed-form router calibration that improves merged model performance without retraining.
CRANE applies magnitude thresholding, a Conservative Taylor Gate, and Graduated Sigmoidal Projection to the Thinking-Instruct delta to improve code agent pass rates on Roo-Eval, SWE-bench-Verified, and Terminal-Bench while preserving efficiency.
PivotMerge merges post-alignment cross-modal projectors from heterogeneous MLLM pre-training via shared-space filtering and layer-wise weights, beating prior merging baselines on multimodal benchmarks.
Empirical scaling laws for LLM merging show a size-dependent floor and 1/k-like tail in cross-entropy loss that holds across architectures and merging methods.
ReLoRA reduces time-to-readiness for LoRA adapters on updated LLMs by up to 8.9x through adaptive Bayesian initialization and scheduled regularization while improving accuracy by up to 4.6%.
M2A uses null-space model merging to combine mathematical and agentic reasoning in LLMs, raising SWE-Bench Verified performance from 44.0% to 51.2% on Qwen3-8B without retraining.
Post-processing via random selection or linear combination of differentially private models allows meeting arbitrary target privacy parameters without additional training.
citing papers explorer
-
Discovering Physical Directions in Weight Space: Composing Neural PDE Experts
Fine-tuning neural PDE operators to regime endpoints reveals a physical direction in weight space that CCM uses to compose accurate merged models for new or extrapolated regimes from metadata or short prefixes.
-
When Model Merging Breaks Routing: Training-Free Calibration for MoE
Merging breaks MoE routing via softmax sensitivity; HARC uses Hessian curvature for closed-form router calibration that improves merged model performance without retraining.
-
CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing
CRANE applies magnitude thresholding, a Conservative Taylor Gate, and Graduated Sigmoidal Projection to the Thinking-Instruct delta to improve code agent pass rates on Roo-Eval, SWE-bench-Verified, and Terminal-Bench while preserving efficiency.
-
PivotMerge: Bridging Heterogeneous Multimodal Pre-training via Post-Alignment Model Merging
PivotMerge merges post-alignment cross-modal projectors from heterogeneous MLLM pre-training via shared-space filtering and layer-wise weights, beating prior merging baselines on multimodal benchmarks.
-
Model Merging Scaling Laws in Large Language Models
Empirical scaling laws for LLM merging show a size-dependent floor and 1/k-like tail in cross-entropy loss that holds across architectures and merging methods.
-
ReLoRA: Knowledge-Reusing Adaptation for Fast Rollout of Evolving LLM Services
ReLoRA reduces time-to-readiness for LoRA adapters on updated LLMs by up to 8.9x through adaptive Bayesian initialization and scheduled regularization while improving accuracy by up to 4.6%.
-
M2A: Synergizing Mathematical and Agentic Reasoning in Large Language Models
M2A uses null-space model merging to combine mathematical and agentic reasoning in LLMs, raising SWE-Bench Verified performance from 44.0% to 51.2% on Qwen3-8B without retraining.
-
Differentially Private Model Merging
Post-processing via random selection or linear combination of differentially private models allows meeting arbitrary target privacy parameters without additional training.
- Retrofit: Continual Learning with Controlled Forgetting for Binary Security Detection and Analysis