AINeutralarXiv – CS AI · Jun 256/10
🧠Researchers propose Transfer-Aware Curriculum (TAC), a machine learning optimization technique that dynamically adjusts training priorities across multiple domains by measuring how well improvements in one area transfer to others. The method achieves superior performance on reasoning tasks compared to fixed curricula, suggesting that cross-domain transferability is a critical factor for training more capable AI systems.
🧠 Llama
AIBullisharXiv – CS AI · Jun 256/10
🧠Researchers introduce FORCE, a three-stage reinforcement learning framework that significantly improves the efficiency of fine-tuning Vision-Language-Action models for robotics. By addressing Q-function instability and low-quality exploration data, FORCE achieves 79% absolute improvement in success rates while reducing training time by 32.5%, eliminating the need for human intervention during deployment.
AINeutralarXiv – CS AI · Jun 236/10
🧠Researchers discover that On-Policy Distillation (OPD) in reinforcement learning suffers from position bias, where later tokens in sequences receive degraded supervision as student rollouts deviate from teacher distributions. They propose Importance-Weighted OPD (IW-OPD), which adaptively reweights tokens based on accumulated distribution discrepancy, achieving up to 6.9-point improvements on benchmark tasks.
AIBullisharXiv – CS AI · Jun 236/10
🧠Researchers introduce DataClaw0, an AI system that actively refines and structures unstructured multimodal data streams to align with specific user and downstream task intents. The 9B-parameter model uses a two-stage pipeline combining supervised fine-tuning with reinforcement learning, validated through a new benchmark and demonstrated improvements in video generation, VQA, and GUI navigation tasks.
AIBullisharXiv – CS AI · Jun 196/10
🧠Researchers introduce the Independent Combinatorial Tokens (ICT) framework to improve Large Language Model reasoning by addressing entropy collapse and explosion problems in reinforcement learning. Using Jensen-Shannon divergence to identify critical token branching points, ICT achieves 4.58% average improvement in pass@4 scores across math, commonsense, and Olympiad benchmarks on Qwen models.
AINeutralarXiv – CS AI · Jun 196/10
🧠Researchers propose Bayesian Manifold Curriculum (BMC), a new framework for training large language models through reinforcement learning that treats problem sampling as a structured bandit problem rather than independent tasks. The approach organizes problems hierarchically and balances difficulty, diversity, and task relevance, showing that difficulty alone is insufficient for optimal model improvement.
AINeutralarXiv – CS AI · Jun 116/10
🧠Researchers introduce ERTS, an explainability-based training method that reduces computational costs for ECG classification by using attention map quality to identify which training samples are genuinely informative versus noisy. The approach demonstrates consistent performance improvements across multiple datasets while significantly lowering training expenses, offering practical efficiency gains for resource-constrained healthcare environments.
AIBullisharXiv – CS AI · Jun 96/10
🧠Researchers introduce Stage-Aware Dynamic Weighting (SAW), a novel mechanism for multi-objective reinforcement learning in large language models that addresses the asynchronous nature of reward learning across different objectives. By using coefficient of variation as a real-time informativeness proxy, SAW dynamically reweights objective contributions to improve training efficiency and final performance with minimal computational overhead.
AINeutralarXiv – CS AI · Jun 96/10
🧠Researchers propose a reinforcement learning technique that accelerates policy training by gradually transferring control from a baseline policy to a learnable policy, achieving faster convergence and superior performance compared to training from scratch while maintaining high success rates throughout the learning process.
AIBullisharXiv – CS AI · Jun 96/10
🧠Researchers have reformulated Predictive Coding (PC), a brain-inspired neural network training method, to address its severe computational inefficiency in digital systems. The new error-based PC (ePC) eliminates signal decay problems inherent in the canonical state-based formulation, achieving backpropagation-level performance at orders of magnitude faster speeds, enabling PC to scale to deeper architectures on standard hardware.
AIBullisharXiv – CS AI · Jun 86/10
🧠Researchers introduce WAV v1, a multi-resolution residual routing technique that improves deep transformer training by capturing directional detail in residual connections beyond simple block summaries. The method shows significant performance gains at 48-layer depths, reducing validation loss by 2.2% on TinyStories and 0.6% on Text8 with minimal parameter overhead.
AINeutralarXiv – CS AI · Jun 56/10
🧠Researchers propose TAPO (Tool-Aware Policy Optimization), a method that fixes credit misassignment problems in reinforcement learning for multimodal search agents. The technique improves training efficiency for AI systems that use tools, delivering consistent improvements across multiple benchmarks without requiring additional annotations or computational overhead.
AIBullisharXiv – CS AI · Jun 56/10
🧠Researchers introduce Selective-Advantage Adaptive-Horizon GRPO (SA-AH-GRPO), an improved reinforcement learning algorithm for language models that applies asymmetric token-level discounting to stabilize training on reasoning tasks. The method achieves 3.6x reduction in training variance while maintaining peak performance on mathematical reasoning benchmarks, demonstrating more efficient model alignment without sacrificing accuracy.
AINeutralarXiv – CS AI · Jun 56/10
🧠Researchers introduce RREDCoT, a novel method for improving reasoning language models by redistributing rewards at the segment level during reinforcement learning training. The approach addresses the high variance problem inherent in current Chain-of-Thought optimization methods by using the model itself to estimate which parts of reasoning traces deserve higher rewards, without requiring expensive additional computation.
AINeutralarXiv – CS AI · Jun 56/10
🧠Researchers propose semi-offline reinforcement learning, a novel paradigm that bridges online and offline RL approaches to optimize text generation. The method balances exploration costs with training efficiency while providing theoretical frameworks for comparing different RL settings, demonstrating comparable or superior performance to existing state-of-the-art methods.
AINeutralarXiv – CS AI · Jun 46/10
🧠Researchers trained a small 86M-parameter language model on Indonesian arithmetic using pedagogically-grounded Chain-of-Thought supervision based on the GASING method, achieving over 80% accuracy on held-out problems. The model developed both procedural reasoning and mental-arithmetic capabilities without reinforcement learning, demonstrating that human teaching methods can guide efficient AI training for mathematical reasoning.
AINeutralarXiv – CS AI · Jun 46/10
🧠Researchers demonstrate that Muon, an optimizer for large language model training, outperforms Adam by approximately 2x efficiency through lower Normalized Directional Sharpness (NDS) rather than smaller update scales. Using curvature analysis and stylized quadratic problems, the work reveals that Muon's advantage stems from better balancing of update energy across heterogeneous curvature regions, with benefits amplified in data-imbalanced scenarios.
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers propose CAST, a new self-distillation method for reinforcement learning in large language models that improves upon existing approaches by using answer-free teacher scoring and bidirectional advantage flipping. The method addresses limitations in Group Relative Policy Optimization (GRPO) by providing denser token-level guidance while maintaining alignment with trajectory correctness, demonstrating improvements in mathematical reasoning tasks.
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers propose Credit-Attenuated Privileged Feedback (CAPF), a training mechanism that guides LLM search agents by providing verifier feedback during training to improve learning on difficult problems. The approach improves performance on open-domain QA benchmarks by leveraging information already available in reinforcement learning systems, increasing exact-match accuracy from 44.7% to 48.5% on Qwen3-4B.
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers propose ARCA, a new token-level credit assignment method for language model reinforcement learning that addresses degradation issues in parameter-efficient fine-tuning approaches like LoRA. By measuring where adapters actually modify hidden states rather than tracking output distribution shifts, ARCA provides non-degenerate credit signals competitive with existing baselines while requiring no additional learned components.
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers discover fundamental limits in using token reduction techniques to accelerate unified vision-language model training, finding that visual understanding and generation have conflicting computational requirements. While task-specific optimization achieves efficiency gains individually, joint training creates synergy loss, suggesting that efficient unified VLM development requires new approaches that preserve cross-task parameter sharing.
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers propose Efficient Layer Attention (ELA), a novel neural network architecture that reduces redundancy in layer attention mechanisms through KL divergence quantification and Enhanced Beta Quantile Mapping. The approach achieves 30% faster training times while improving performance on image classification and object detection tasks.
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers introduce Margin-Adaptive Direct Preference Optimization (MADPO), a novel method that improves large language model alignment by using a reward model to apply instance-level adaptive weights to training samples. MADPO addresses limitations in existing approaches like DPO and β-DPO by providing stable, granular control over the learning signal without discarding training data.
AIBullisharXiv – CS AI · Jun 26/10
🧠Researchers propose DynMuon, an enhancement to the Muon optimizer used in large language model training that dynamically adjusts spectral shaping parameters throughout training. The method achieves lower validation loss and requires 10.6-26.5% fewer training steps than standard Muon by shifting from positive to mildly negative spectral exponents.
$UV
AINeutralarXiv – CS AI · Jun 16/10
🧠LARK introduces a learnability-grounded approach to trajectory selection for reasoning distillation, enabling student models to learn more efficiently from teacher-generated reasoning paths. The method uses a learnability factor to identify trajectories that maximize learning speed while maintaining distributional coverage, outperforming existing heuristic-based selection methods across multiple reasoning tasks.
