ACE-SQL jointly optimizes schema linking and SQL generation via RL with empirical credit assignment from execution-correct rollouts, achieving 65.3% greedy execution accuracy on BIRD Dev using 0.93k output tokens.
Gradient surgery for multi-task learning
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Hybrid CFD-MOMARL framework with PCGrad enables micro-swarm navigation in pulsatile flow, achieving progress 6.5-7.0, energy 0.63-0.65, smoothness 0.97-0.99 with emergent behaviors.
T3R applies multiple Rotograd matrices and a rotation technique to create surrogate gradients, enabling deeper test-time adaptation in GNNs and yielding 0.172 MAE reduction plus 9.37% relative gains on OGB benchmarks.
Quantum ring all-reduce halves per-link communication via superdense coding and enables composable ε-secure aggregation at 2x GHZ overhead, plus quantum advantages in gradient conflict detection.
Local low-rank task-gradient structures exist in weights and activations but are non-stationary, with initial recovery updates forming a basis capturing 77% of LoRA displacement and parameter steps aligning 0.58 cosine with CAA steering vectors.
SALT is a subspace-adaptive plug-in for GRPO that decomposes group-relative coefficients into shared and residual channels using mini-batch Gram geometry and amplifies residuals to mitigate signed cancellation in RLVR.
Frontier LLMs' self-declared language support is unstable and over-optimistic, verified behavior is task-dependent, and language mismatch alone degrades collaborative agent performance.
COMPASS uses semantic clustering on multilingual embeddings to select auxiliary data for PEFT adapters, outperforming linguistic-similarity baselines on multilingual benchmarks while supporting continual adaptation.
A large multi-task multi-domain robot dataset combined with 50 new demonstrations yields 2x higher success rates on never-before-seen tasks in new domains.
An empirical audit of 22 JEPA-style training auxiliaries on Llama-3.2-1B fine-tuning for regex generation finds no statistically significant task improvement after multiple-testing correction, even when auxiliaries visibly alter hidden-state geometry.
The paper reviews limits in AI vision for robotics and describes work-in-progress on bridging sim-to-real domain gaps by linking real and synthetic training data.
Presents a generalized mathematical operator framework that defines conflict as an independent, context-sensitive object integrating weighting, scale, and mapping components.
citing papers explorer
-
ACE-SQL: Adaptive Co-Optimization via Empirical Credit Assignment for Text-to-SQL
ACE-SQL jointly optimizes schema linking and SQL generation via RL with empirical credit assignment from execution-correct rollouts, achieving 65.3% greedy execution accuracy on BIRD Dev using 0.93k output tokens.
-
Micro-Swarm Locomotion Optimization in Dynamic Flow using Multi-Objective Multi-Agent Reinforcement Learning
Hybrid CFD-MOMARL framework with PCGrad enables micro-swarm navigation in pulsatile flow, achieving progress 6.5-7.0, energy 0.63-0.65, smoothness 0.97-0.99 with emergent behaviors.
-
T3R: Deeper Test-Time Adaptation for Graph Neural Networks via Gradient Rotation
T3R applies multiple Rotograd matrices and a rotation technique to create surrogate gradients, enabling deeper test-time adaptation in GNNs and yielding 0.172 MAE reduction plus 9.37% relative gains on OGB benchmarks.
-
Quantum ring all-reduce: communication and privacy advantages for distributed learning
Quantum ring all-reduce halves per-link communication via superdense coding and enables composable ε-secure aggregation at 2x GHZ overhead, plus quantum advantages in gradient conflict detection.
-
Recoverable but Not Stationary:Local Linear Structures in Weights and Activations
Local low-rank task-gradient structures exist in weights and activations but are non-stationary, with initial recovery updates forming a basis capturing 77% of LoRA displacement and parameter steps aligning 0.58 cosine with CAA steering vectors.
-
SALT: When More Rollouts Don't Help in Group-Based Policy Optimization and How to Make Them Matter
SALT is a subspace-adaptive plug-in for GRPO that decomposes group-relative coefficients into shared and residual channels using mini-batch Gram geometry and amplifies residuals to mitigate signed cancellation in RLVR.
-
Lost in the Tower of Babel: The Adverse Effects of Incidental Multilingualism in LLMs
Frontier LLMs' self-declared language support is unstable and over-optimistic, verified behavior is task-dependent, and language mismatch alone degrades collaborative agent performance.
-
COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling
COMPASS uses semantic clustering on multilingual embeddings to select auxiliary data for PEFT adapters, outperforming linguistic-similarity baselines on multilingual benchmarks while supporting continual adaptation.
-
Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets
A large multi-task multi-domain robot dataset combined with 50 new demonstrations yields 2x higher success rates on never-before-seen tasks in new domains.
-
Representation Without Reward: A JEPA Audit for LLM Fine-Tuning
An empirical audit of 22 JEPA-style training auxiliaries on Llama-3.2-1B fine-tuning for regex generation finds no statistically significant task improvement after multiple-testing correction, even when auxiliaries visibly alter hidden-state geometry.
-
Efficiently Linking Real Scenes with Synthetic Data Generation for AI-based Cognitive Robotics and Computer Vision Applications
The paper reviews limits in AI vision for robotics and describes work-in-progress on bridging sim-to-real domain gaps by linking real and synthetic training data.
-
A Mathematical Conflict Framework for Contextual Data Modulation
Presents a generalized mathematical operator framework that defines conflict as an independent, context-sensitive object integrating weighting, scale, and mapping components.