8450 papers
This paper challenges prior claims of Best-of-N's suboptimality by demonstrating that, under practical assumptions and when evaluated via win-rate rather than expected reward, properly tuned Best-of-N is both statistically and computationally optimal, while also proposing a simple variant that eliminates reward hacking without sacrificing performance.
This paper introduces Icarus, a deep learning-based all-weather sky model that overcomes the limitations of existing methods in handling full dynamic range and class-imbalanced solar regions to generate photorealistic, user-controllable environment maps for accurate Image-Based Lighting.
The paper introduces MIRACL, a novel hierarchical Meta-MORL framework that enables few-shot generalization and efficient adaptation for multi-objective multi-echelon supply chain optimization by decomposing tasks into structured subproblems and employing a Pareto-based strategy to achieve superior performance over conventional baselines.
This paper introduces Score-Guided Proximal Projection (SGPP), a unified geometric framework that reformulates Rectified Flow editing as a proximal optimization problem to overcome the limitations of existing inversion and sampling methods by theoretically guaranteeing manifold convergence while enabling a continuous, training-free trade-off between identity preservation and generative flexibility.
This paper introduces TML-Bench, a benchmark for evaluating the end-to-end correctness and reliability of autonomous coding agents on Kaggle-style tabular machine learning tasks, demonstrating that the MiniMax-M2.1 model achieves the best aggregate performance across four competitions under varying time budgets.
This paper introduces SCORE, a novel model merging method that resolves singular subspace conflicts between domain-specific models by projecting them into a shared orthogonal basis, thereby significantly improving generalization to unseen domains compared to existing approaches.
This paper proposes the Disentangled Safety Hypothesis (DSH), which reveals that large language models separate safety "recognition" and "refusal execution" into distinct geometric subspaces, enabling the development of the Refusal Erasure Attack (REA) to bypass safety mechanisms by surgically disabling the refusal axis while preserving harmful content generation.
This paper proposes a first-order Softmax-Weighted Switching Gradient method for distributed stochastic minimax optimization under stochastic constraints, achieving optimal oracle complexity and high-probability convergence guarantees in both full and partial client participation settings while avoiding the instability of traditional primal-dual approaches.
This paper introduces temporally sensitive Alternation (ALT) metrics to reveal that conventional outcome-based evaluations can severely mischaracterize multi-agent coordination, as demonstrated by Q-learning agents in a Battle of the Exes variant that achieve high traditional fairness scores but perform significantly worse than random baselines in actual turn-taking dynamics.
This paper utilizes crosscoders to demonstrate that Mixture of Experts (MoE) models develop more specialized, focused representations with fewer unique features compared to the broader, general-purpose feature distributions found in dense models of equivalent active parameter count.
This paper analyzes the DeepSeekMoE model to reveal that Mixture of Experts architectures exhibit highly concentrated specialization where a single dominant expert can approximate full ensemble performance, suggesting significant opportunities for inference optimization through targeted expert pruning.
This paper introduces Margin and Consistency Supervision (MaCS), an architecture-agnostic regularization framework that combines a hinge-squared margin penalty and a consistency regularizer to simultaneously enhance the calibration, robustness, and generalization of deep vision models without requiring additional data or architectural changes.
The paper introduces SEA-PEFT, a self-auditing parameter-efficient fine-tuning framework that automates adapter configuration through a dynamic search-audit-allocate loop, achieving significant performance improvements in few-shot 3D medical image segmentation without requiring manual design or extensive computational resources.
This paper empirically evaluates the effectiveness and limitations of many-shot prompting for test-time adaptation in large language models, finding that while it benefits structured tasks with high information gain, its performance is highly sensitive to selection strategies and often yields limited improvements for open-ended generation.
ReflexiCoder is a novel reinforcement learning framework that internalizes structured self-reflection and self-correction capabilities into an LLM's weights, enabling it to autonomously generate, debug, and optimize code without external feedback while achieving state-of-the-art performance and improved token efficiency across multiple benchmarks.
The paper introduces STEP, a continuous-time stochastic framework that models temporal link prediction as a sequential forecasting problem via Poisson-driven motif transitions, achieving significant precision gains and lower runtime compared to state-of-the-art baselines while remaining compatible with existing graph neural networks.
This paper proposes ROSE, a reordered SparseGPT method that enhances one-shot LLM pruning accuracy by adaptively reordering weights based on estimated column and block pruning losses to address the suboptimal performance caused by predefined left-to-right pruning orders in layers with columnar patterns.
PixARMesh is a novel autoregressive method that directly reconstructs complete, high-fidelity, and artist-ready 3D indoor scene meshes from a single RGB image by jointly predicting object layout and geometry within a unified model, eliminating the need for implicit fields or post-hoc optimization.
This paper proposes three bias mitigation techniques—top-k concept filtering, removal of biased concepts, and adversarial debiasing—to address information leakage in Concept Bottleneck Models, thereby achieving superior fairness-performance tradeoffs for interpretable image classification compared to prior work.
This paper introduces Reference-guided Policy Optimization (RePO), a novel framework that combines reinforcement learning with verifiable rewards and supervised reference guidance to effectively balance exploration and exploitation in molecular optimization tasks where only single-reference data is available, thereby outperforming existing SFT and RLVR baselines.