The paper introduces Weak-Critic Strong Oversight, a method where a weak model guides a strong model's self-improvement by providing non-misleading revision directions, leading to scalable oversight.

The paper proposes using fine-grained quality signals, such as pairwise self-judgments and token-level entropy, instead of simple binary correctness to improve LLM performance on saturated datasets, s…

ResMerge proposes a residual-based spectral merging framework that improves the combination of multiple reinforcement learning (RL) expert models by stabilizing the aggregation process using a residua…

The paper introduces the Triangulated Preference Shift score, an automated, curation-free metric to quantify systematic lexical biases introduced into Large Language Models during the preference-learn…

The paper identifies a failure mode called spatial lexical bias in MLLMs, where adding a spatial word to options biases the model's choice, and demonstrates that this failure originates primarily from…

MARS proposes an encoder-agnostic aggregation operator that explicitly models multi-scale temporal structure in sequential recommendation, achieving state-of-the-art performance across both sparse and…

The paper proposes FedSAP, a framework that stabilizes federated prototype learning by delaying global alignment and enforcing inter-class structure, significantly improving representation quality und…

The paper proposes S2L-PO, a framework that uses smaller, naturally diverse models as structured explorers to enhance the policy-level diversity and performance of larger language models during traini…

S-SPPO introduces a dual-space semantic calibration framework to stabilize Self-Play Preference Optimization (SPPO), preventing policy degeneration when preference oracles assign overly confident wins…

The paper introduces CoRP, a gradient-free operator that consolidates the benefits of ensemble-based post-training methods into a single, deployable model update, significantly improving performance w…

The paper introduces Responsible Contrastive Soft Prompting (RCSP), a parameter-efficient method using soft prompts to improve LLM reliability by simultaneously suppressing hallucinations, encouraging…

The paper proposes Sensitivity-Uncertainty Alignment (SUA), a framework that measures the misalignment between a model's prediction instability and its stated uncertainty to improve model reliability.

The paper proposes Visual Gradient Steering (VGS), a method that decomposes the distillation loss into language and visual components and steers the optimization to prioritize visual grounding, signif…

The paper introduces Drifting Preference Optimization (DrPO), an efficient online method for preference finetuning one-step text-to-image generators that avoids complex gradient calculations and model…

The paper proposes EAGLE, a novel evidence-aligned multi-agent framework, demonstrating that requiring shared visual evidence among agents is crucial for achieving reliable and trustworthy consensus i…

The paper demonstrates that jointly training a single lightweight neural reranker on multiple diverse environments significantly improves action selection performance and achieves positive cross-domai…

The paper investigates the limits of self-evolution in LLM reasoning under closed-loop settings, finding that while self-improvement is significant, it consistently falls short of perfect oracle super…

The paper introduces BiAxisAudit, a novel framework that evaluates LLM bias by analyzing bias scores across multiple prompt formats and within the internal inconsistency of model responses, revealing…