paperlist.ai

AI 顶会论文

AI 顶会论文库

检索 30+ 个顶会的论文，包括 NeurIPS、ICLR、ICML、CVPR、ACL、AAAI 等。输入关键词筛选，打开任意一篇查看摘要、作者和链接。

NeurIPS 2026

StarCraft Motion: A Dataset for Agent Simulation in Adversarial and Partially Observable Scenarios

Yi-Chung Chen, Mingyu Kim, Ruqi Bai, James Z Hare, Jing Gao, David Inouye

Agent simulation aims to model the future behavior of interacting agents, but existing benchmarks have largely focused on structured domains such as autonomous driving. Adversarial and partially observable settings remain less explored, despite their importance for modeling strategic multi-agent behavior. To address this gap, we introduce StarCraft Motion, a large-scale dataset for agent simulation built from human StarCraft~II replays. Our processing pipeline converts raw replays into standardized simulation scenarios by extracting continuous unit trajectories, deriving command-based unit-level intent labels, and aligning game states with player-specific fog-of-war observations. This enables direct study of behavior, intent, and opponent responses under competitive partial observability. As an initial study, we evaluate autoregressive simulation methods on StarCraft Motion and introduce HMART, a hierarchical baseline that extends SMART with learnable player-level query aggregation for efficient global-context modeling in large-agent-count scenarios. Experiments show that global context improves observer-unit simulation and intent prediction, while closed-loop fine-tuning further improves rollout quality. However, accurately capturing intent initiation and transitions remains difficult. We also find that opponent modeling from partial observations is substantially more challenging, and that additional global information can be misleading when it does not match the opponent's perspective. These results highlight StarCraft Motion as a useful dataset for studying scalable agent simulation in adversarial, partially observable environments.

NeurIPS 2026

Standing on the Shoulders of Giants: Rethinking EEG Foundation Model Pretraining via Multi-Teacher Distillation

Chenqi Li, Yu Liu, Shuo Zhang, Timothy Denison, Tingting Zhu

Pretraining for electroencephalogram (EEG) foundation models has predominantly relied on self-supervised masked reconstruction, a paradigm largely adapted from and inspired by the success of vision and language foundation models. However, unlike images and text, EEG datasets are notoriously expensive to collect and characterized by low signal-to-noise ratio. These challenges introduce difficulties in scaling the EEG foundation models and capturing the underlying neural semantics through reconstruction. In this work, we ask the question: can we stand on the shoulders of well-established foundation models from well-represented modalities to bootstrap the pretraining of EEG foundation models? We first demonstrate that mainstream foundation models, such as those from vision and time series, transfer surprisingly well to EEG domain. Motivated by this observation, we propose the multi-teacher distillation pretraining (MTDP) framework for pretraining EEG foundation models via two-stage multi-teacher distillation. In the first stage, we introduce a learnable gating network to fuse representations from diverse teachers (e.g., DINOv3 and Chronos) via a masked latent denoising objective. In the second stage, we distill the fused representation into an EEG foundation model. Extensive evaluations across 2 backbone architectures, 9 downstream tasks and 12 datasets demonstrate that multi-teacher distillation pretraining consistently outperforms self-supervised pretraining for EEG foundation model and remains competitive even when the pretraining data is reduced to 25%.

NeurIPS 2026

StakeBench: Evaluating Language Understanding Grounded in Market Commitment

Yunhua Pei, Jingyu Hu, Yiwei Shi, Hongnan Ma, Weiru Liu, John Cartlidge

Existing financial NLP benchmarks often rely on labels supplied by outside observers, measuring how language is perceived rather than what speakers have committed to in the market. We introduce \textbf{StakeBench}, an evaluation framework for language understanding grounded in market commitment. StakeBench links 560,876 comments from 2,261 resolved markets to verified position, action, and market-odds records across Polymarket and Manifold. Supervision is derived from observable market behavior. Position sides, post-comment trading actions, and market-odds trajectories replace human annotation. Four diagnostic tasks test whether models detect market commitment, identify the revealed side, anticipate future action, and perform collective odds projection. Three commitment-aware metrics measure alignment with revealed preferences rather than perceived sentiment. Validity audits and explicit interpretation boundaries help distinguish observable commitment signals from latent belief and causal market-odds impact. Across 15 LLMs and 18 topics and platform settings, models partially recover position-side signals, with Directed Accuracy from 0.506 to 0.599, but show structural failures on later tasks. Ten of the fifteen models collapse to one or two action labels in future action anticipation, and no model consistently improves on the naive odds-direction baseline in collective odds projection. Model scale is not correlated with performance, finance-domain tuning does not improve revealed-side identification, and platform incentives strongly shape higher-order results. StakeBench is packaged with evaluation code and dataset under CC-BY~4.0.

NeurIPS 2026

StainNFT: Curriculum-Gated Multi-Reward Post-Training for Pathology-Faithful Virtual Staining

shurong yang, Dong Wei, Qiong Peng, Xian Wu, Yefeng Zheng, Liansheng Wang

Immunohistochemical (IHC) staining encodes molecular protein expression critical for clinical diagnosis, yet its chemical procedures are costly and time-consuming. Virtual staining offers a compelling alternative by digitally synthesizing IHC images from hematoxylin-eosin (H\&E) stained slides. Despite remarkable progress in diffusion- and flow-matching-based virtual staining, supervised fine-tuning (SFT) remains fundamentally limited in pathological fidelity due to its coarse, spatially averaged supervision signal that starves sparse DAB-positive regions of effective gradients. Reinforcement learning (RL) can exploit inter-rollout variance for outcome-level pathological supervision, but naively applying DAB-based rewards triggers severe reward hacking that collapses the image distribution and degrades perceptual quality. This paper presents StainNFT, a flow matching RL post-training framework built on a curriculum reward strategy that gates fine-grained optical density supervision on per-sample DAB mask IoU. To enhance fine-grained pathological fidelity, we introduce expression-aware reweighting, multi-scale block supervision, and a closed-loop implicit pathological semantic reward derived from pathology foundation model priors. Extensive experiments on seven benchmarks demonstrate that StainNFT consistently outperforms existing methods in both perceptual quality and pathological fidelity for H\&E-to-IHC virtual staining. Ablation studies confirm the effectiveness of each proposed component. Our code and trained models will be released.

NeurIPS 2026

Stage-wise Attention-Guided Region Sequencing for Adversarial Attacks on Large Vision-Language Models

Jaehyun Kwak, Nam Cao, Boryeong Cho, Segyu Lee, Sumyeong Ahn, Se-Young Yun

Targeted adversarial attacks on Large Vision-Language Models (LVLMs) test whether small image perturbations can steer model responses toward attacker-specified content. Under the standard $L_\infty$ constraint, targeted attacks become a regional perturbation budget allocation problem: attack success depends not only on the perturbation objective, but also on which regions receive updates and in what order. Existing localized attacks improve over global perturbations but rely on stochastic spatial sampling, often updating weakly influential regions. We address this limitation through an attention-based analysis showing that cross-modal attention identifies adversarially sensitive regions and that perturbing high-attention hotspots induces predictable redistribution toward subsequent salient regions. These findings motivate attention-guided region sequencing, which begins from dominant hotspots and progressively moves the update support toward next-salient regions. Based on these principles, we propose Stage-wise Attention-Guided Attack (SAGA), a black-box region-sequencing framework that uses a fixed attention map from an open-source LVLM to guide perturbation updates without accessing target-model parameters, gradients, or attention maps. Across ten closed-source and open-source LVLMs, SAGA achieves state-of-the-art attack success rates and the best overall imperceptibility.

NeurIPS 2026

Stage-Aware Dual Alignment for Covariate Shift in Graph Domain Adaptation

Hongwei Wen, Can Zhang, Haoyu He, Xintao Zhao, Hanyuan Hang, Minglong Lei

The performance of *Graph Domain Adaptation* (*GDA*) is fundamentally limited by *covariate-driven* discrepancies between source and target graphs, captured by *Covariate Shift* (*CS*) in the joint feature-structure space beyond label-related formulations. We show that CS induces bias at two non-interchangeable stages of *Graph Neural Network* (*GNN*) computation: *Feature Shift* (*FS*) distorts representations before message passing, while *Feature-Conditional Structure Shift* (*FCSS*) biases propagation, rendering single-stage alignment intrinsically insufficient. Based on this, we propose *Dual Alignment for Covariate Shift* (*DACS*), a stage-aware GDA framework that aligns discrepancies at their source. DACS mitigates FS via adversarial feature alignment and addresses FCSS through layer-wise reweighting to correct propagation bias, followed by final adversarial alignment for residual mismatch. This design follows directly from the stage-wise structure of CS rather than heuristic combinations of alignment modules. We further show that representation and propagation biases correspond to distinct components of target-domain error that cannot be eliminated in isolation. Experiments on synthetic and real-world benchmarks demonstrate that DACS consistently outperforms prior methods, especially under complex and coupled distribution shifts.

NeurIPS 2026

StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer Training

Bao Tang, JiaHao Guo, Haoxiang Cao, Wenyu Liu, Changqian Yu, Kun Gai, Xinggang Wang

Vector Quantization (VQ) is fundamental to discrete visual tokenizers that power modern autoregressive and masked image generation models. While recent shared-projection codebook methods have substantially advanced codebook utilization, training stability remains a critical and underexplored challenge. We argue that the root cause lies in the entanglement of the Encoder--Decoder and Codebook training: because neither module can reliably fulfill its own responsibility in isolation, the system can only function when the two subsystems happen to cooperate---a fragile condition that breaks down precisely when training is most stressed. We propose StableVQ, which revisits the proper learning objective of each module and resolves the problems that arise when each is trained to fulfill its own role independently. Concretely, (1) Dynamic STE corrects the instability in the Encoder's learning objective, enabling it to robustly optimize the reconstruction space under discrete regularization even when codebook utilization is low. (2) Region VQ Loss reconceives the Codebook's learning objective so that it can independently guarantee full tracking of the encoder output distribution, without relying on encoder oscillations to drive activation. (3) Decoupled Schedule recognizes that the distinct responsibilities of the Encoder--Decoder and the Codebook demand distinct optimization dynamics, and assigns each an independent learning rate schedule to ensure robust system-level behavior. Built on top of shared-projection codebooks, StableVQ is lightweight and introduces no learnable parameters. Experiments on ImageNet demonstrate consistent improvements in training stability, codebook utilization, and reconstruction quality across diverse codebook sizes and initialization settings.

NeurIPS 2026

StableAvatar: Ultra-Long Audio-Driven Avatar Video Generation

Shuyuan Tu, Yueming Pan, Yinming Huang, Xintong Han, Zhen Xing, Qi Dai, Chong Luo, Zuxuan Wu, Yu-Gang Jiang

Current diffusion models for audio-driven avatar video generation struggle to synthesize long videos with natural audio synchronization and identity consistency. This paper presents StableAvatar, the first end-to-end video diffusion transformer that synthesizes ultra-long videos. We observe that the primary reason preventing existing models from generating long videos is their audio modeling, which typically relies on third-party off-the-shelf audio embeddings that are introduced into the diffusion model via cross-attention. Since current diffusion backbones lack any audio-related priors, they cannot correctly couple audio cues with latent dynamics, causing systematic latent distribution deviations at each segment. These deviations accumulate across segments, gradually shifting the latent trajectory and producing noticeable quality drift. To address this, StableAvatar introduces a novel Timestep-aware Audio Adapter that prevents error accumulation via timestep-aware modulation. During inference, we propose a novel Audio Native Guidance Mechanism to further enhance the audio synchronization by leveraging the diffusion’s joint audio-latent prediction as a dynamic guidance signal. To enhance the smoothness of the ultra-long videos, we introduce a Dynamic Weighted Sliding-window Strategy that fuses latent over time. Experiments on benchmarks show the effectiveness of StableAvatar both qualitatively and quantitatively.

NeurIPS 2026

Stable3R: Streaming 3D Reconstruction with Stable Geometric References

Jincheng Xiong, Jiarong Han, Hang Zhang, Mu Xu, Ming Qian

Streaming 3D reconstruction has become a critical component for real-time applications. While recent advances have adapted large-scale offline feedforward models into streaming architectures via causal attention and KV-caching, they suffer from fundamental instability: the irreversible bias in early frames. This limitation stems from two coupled factors: (1) the existing KV-cache-based causal architecture strictly prohibits access to future information, resulting in information-poor early caches; and (2) current methods typically anchor the pose constraints to the initial frame, amplifying the early bias throughout the sequence. To address these challenges, we propose Stable3R, a holistic framework that establishes stable geometric references by enriching historical caches and anchoring poses to prefixes rather than a single initial frame. Specifically, we first introduce a lookahead-augmented attention mechanism, integrating future observations into past caches without violating causal constraints. Second, we adopt a frame-equivariant architecture with prefix-relative supervision, alleviating the reliance on the biased initial frame. Extensive experiments across multiple benchmarks show that our method consistently boosts reconstruction quality within a strictly causal inference schedule.

NeurIPS 2026

Stable and Scalable Probabilistic Numerical Solvers for Stiff and High-Dimensional ODEs

Nathanael Bosch

Filtering-based probabilistic numerical solvers for ordinary differential equations (ODEs) have been established as a flexible and efficient simulation framework with built-in numerical uncertainty quantification. However, problems that are both stiff and high-dimensional remain a challenge, as current methods are either stable and have cubic cost in the ODE dimension, or scale linearly at the expense of stability. In this paper, we close this gap and develop probabilistic ODE solvers that are both stable and scalable. We propose two complementary strategies. First, we develop a matrix-free update step that uses Jacobian-vector products, iterative linear solvers, and stochastic covariance estimation to enable linear scaling, all while retaining stability. Second, we propose iterative re-linearization to further improve stability without sacrificing scalability, turning probabilistic ODE solvers into fully implicit methods. We evaluate the proposed approaches on a range of stiff and high-dimensional problems and demonstrate improved stability and scalability over established probabilistic solvers.

NeurIPS 2026

Stable and Granular Policy Optimization for Generative Recommendation

Muyu Zou, Haibo Xing, Hao Deng, Zhezheng Hao, Jinxin Hu, Jiawei Chen, Yun Chen, Yu Zhang, Xiaoyi Zeng

Generative recommendation (GR), which directly generates sequential semantic IDs for items, has recently attracted increasing attention in recommender systems. Given that core recommendation metrics are inherently evaluated at the sequence level, reinforcement learning (RL) serves as a natural optimization framework. However, adapting recent group-based RL algorithms to GR presents notable challenges: token-level methods such as GRPO exhibit much more severe training instability, while sequence-level methods such as GSPO enforce uniform token weighting and thus ignore the heterogeneous roles of tokens. To address this dilemma, we propose Stable and Granular Policy Optimization (SGPO), a group-based RL algorithm tailored for GR. SGPO maintains a sequence-level ratio to promote optimization stability while injecting fine-grained token-wise advantages. By incorporating token log-probabilities and reward signs, SGPO explicitly upweights high-confidence tokens in positive trajectories to reinforce successful retrieval, while strictly penalizing them in negative trajectories to encourage exploration, and uses an adaptive scaling factor to bound the variance of reshaped advantages. Experiments on two public benchmarks and a billion-scale industrial dataset show that SGPO consistently outperforms six strong RL baselines and, when deployed on a commercial platform, achieves a 2.36% lift in click-through rate (CTR) and a 1.95% increase in advertising revenue in online A/B testing.

NeurIPS 2026

Stable Resolution-Invariant Emulation in Entropically Controlled Kinetic Methods

Kareem Hegazy, Jose Antonio Lara Benitez, Anastasis Kratsios, Ivan Dokmanic, Maarten v. de Hoop, Michael Mahoney

Resolution invariance is a critical capability for scientific machine learning methods (SciML), however, the ability to sample at any resolution does not guarantee stable emulation at all resolutions. This important distinction underpins one of scientific machine learning's greatest potential: the ability to efficiently emulate complicated and computationally expensive systems on inexpensive coarse grids. Stable numerical solvers are computationally expensive as they attempt to resolve small scales that receive and dissipate spectral energy. Learned coarse-grid forecasters remove the dissipative channel, allowing unresolved frequencies to re-emerge as grid-scale noise (aliasing). We explore stable resolution invariant emulation through physically principled control over entropy dynamics to reinforce the dissipative mechanism within the Neural Discrete Equilibrium (NeurDE) method. Entropically-stabilized NeurDE produces stable long-time rollouts for thousands of forecasting steps on large Reynolds number turbulent flows (Re=50,000) with very coarse grids ($\mathbb{R}^{16\times16}$). Entropically-stabilized NeurDE demonstrates extreme stability at coarse resolutions, outperforming the data-generating stabilized numerical method: a much more challenging baseline than SciML surrogates.

NeurIPS 2026

Stable Partial Order Constraints for Temporal Causal Structure Learning

Changxin Rong, Xiangyu Wang, Taiyu Ban, Yanze Gao, Xingjian Lin, Huanhuan Chen

Temporal causal structure learning aims to recover lag-aware causal relations from multivariate time series. While prior knowledge has been widely used to improve static structure learning, its integration into lag-aware structure learning remains limited, because available priors are often lag-agnostic. Recent studies have explored lag-agnostic edge presence priors, but partial order priors, which can prune the ordering space and improve structure learning, remain underexplored. A key challenge is that variables may influence each other at different lags, leading to cyclic variable-level relations where ordering is no longer naturally defined. Moreover, directly applying static differentiable formulations of partial order constraints can be unstable due to repeated-walk accumulation on cycles. To address this gap, we represent partial order priors on the summary graph and follow the natural idea of the order relation that only allows a single direction of possible causality between two variables, which is equivalent to forbidding all reversed causality, direct or indirect. This converts partial order constraints into path prohibition constraints that can be extended to cyclic summary structures. For stable differentiable characterization, we propose a decoupled partial order constraint method. The method preserves the original lag-aware structure for data fitting, imposes partial order constraints through a normalized summary representation, and captures higher-order reachability with a closed-form connectivity characterization. Experiments further demonstrate its effectiveness in nonstationary settings.

NeurIPS 2026

Stable Max Coverage Under a Cardinality Constraint

Themistoklis Haris, Fabian Spaeh, Nithin Varma, Yuichi Yoshida

We propose a stable algorithm for solving maximum coverage problems under a cardinality constraint of $k$ in a record-level stability model, where adjacent instances $I\sim I'$ differ by the incidence of one universe element. Our algorithm computes a negative-entropy-regularized maximizer of the capped concave relaxation over the hypersimplex and rounds it with a common-seed rounding map from hypersimplex correlated sampling. The resulting sensitivity bound is $\min\{2k, \alpha_k k/\lambda\}$, where $\lambda$ is the regularization parameter and $\alpha_k = O(\log k)$. For utility, the expected coverage has approximation factor $1-\frac{1}{e}$ with an additive error of order $O(\lambda k \log \frac{m}{k})$, where $m$ is the number of input sets. We also report experiments on synthetic and real-world instances.

NeurIPS 2026

Stable Long-Horizon PDE Forecasting via Latent Structured Spectral Propagators

Xiaoxiao Lu, Ye Yuan, Jiahao Shi

Long-horizon forecasting of time-dependent partial differential equations (PDEs) is critical for characterizing the sustained evolution of physical systems. While neural operators have emerged as efficient surrogates, they typically learn implicit finite-time transitions from discrete observations. When deployed autoregressively, such propagators often suffer from rapid error accumulation and dynamic drift. To address this, we propose a neural forecasting framework that reformulates PDE rollout as learning a Structured Spectral Propagator (SSP) in a propagation-oriented latent space. Following an analysis-propagation-synthesis design, our framework: (i) maps physical states into a shared, time-consistent spatial representation; (ii) projects this space into a compact propagation state to isolate recurrent dynamics from fine-grained spatial details, thereby decoupling reconstruction fidelity from rollout regularity; and (iii) evolves retained spectral modes using a frequency-conditioned linear backbone complemented by a nonlinear spectral closure to account for truncated interactions. This explicit structuring endows the propagator with a strong inductive bias for coherent modal evolution. Extensive experiments demonstrate that SSP significantly outperforms state-of-the-art baselines, reducing relative $L_2$ errors by up to 48.9\% and exhibiting improved stability in temporal extrapolation beyond the supervised horizon.

NeurIPS 2026

Stable GFlowNets with Probabilistic Guarantees

Zengxiang Lei, Ananth Shreekumar, Jonathan Rosenthal, Ruoyu Song, Alvaro A. Cardenas, Daniel Fremont, Dongyan Xu, Satish Ukkusuri, Z. Berkay Celik

Generative Flow Networks (GFlowNets) learn to sample states proportional to an unnormalized reward. Despite their theoretical promise, practical training is often unstable, exhibiting severe loss spikes and mode collapse. To address this, we first assess the sensitivity of GFlowNet objectives, demonstrating that a small Total Variation (TV) distance between the learned and target distributions does not preclude an unbounded training loss. Motivated by this mismatch, we establish converse guarantees by deriving loss-to-TV bounds that certify global fidelity from bounded trajectory balance losses. Lastly, we propose \emph{Stable GFlowNets}, which leverages our theory to stabilize training via adaptive reference flow and improves the trade-off among mode coverage, robustness, and certifiability.

NeurIPS 2026

Stable Alpha: Adversarial Invariant Representation Learning for Nonlinear Asset Pricing under Temporal Distribution Shifts

Xiaokang Wang, Zihe Liu, Xinghan Qin, Zihao Yin, Jidong Yuan, Qinxuan Zhang, Xiushuo Hu

Deep learning has emerged as a powerful paradigm for constructing nonlinear asset pricing factor models. However, temporal distribution shifts such as bull-bear transitions and industry rotations undermine the generalization of models trained under the i.i.d. assumption. As a result, existing models tend to exploit environment-specific correlations that are highly predictive in-sample but unstable across market regimes. To address this challenge, we propose $\textit{\textbf{CASH}}$, a causality-inspired asset pricing factor framework designed to learn invariant and minimally sufficient representations under temporal distribution shifts. CASH formulates an information-theoretic adversarial learning objective that systematically discards transient market noise by optimizing against an adversary designed to exploit spurious correlations, thereby distilling invariant factor-return relationships. The resulting invariant representation is then integrated into a conditional factor pricing model via a dynamic factor exposure network. Experiments on real-world stock datasets across multiple markets demonstrate that CASH consistently outperforms state-of-the-art baselines in out-of-sample return prediction and exhibits superior robustness under pronounced temporal regime shifts.

NeurIPS 2026

Stabilizing the Dynamic Low-Rank Training

Zhonghan Xu, Ling Wang, Junhao Chen, Jianwei Zhao, Jinwei Yang

Training neural networks directly in a low-rank parameterization is an appealing route to reducing memory, compute, and storage simultaneously during both training and inference. Dynamic low-rank training (DLRT), which confines weights to a rank-$r$ manifold via the Galerkin projection of the gradient flow, is particularly attractive because it identifies efficient subnetworks on the fly without specialized initialization or post-factorization. However, DLRT fails to find trainable networks under high compression. In this paper, we derive the gradient flow of the best rank-$r$ approximation and point out that the offset of DLRT comes from a curvature-coupling term which is large and thus non-negligible under aggressive compression. Guided by this analysis, we propose a stable dynamic low-rank training method, named SDLRT, which maintains a lightweight compensation buffer that reinjects the top neglected singular directions. Additionally, we introduce a negative feedback on the truncation tolerance to stabilize each layer's rank. Experimentally, SDLRT reliably finds trainable subnetworks where DLRT collapses and as a PEFT adapter on DeBERTa-v3, it achieves the best average score on SuperGLUE at only $2.8\\%$ parameter overhead over LoRA.

NeurIPS 2026

Stabilizing RL+Search for Imperfect-Information Extensive-Form Games

Yinghao Li

RL+Search is the computational backbone of modern AI systems for imperfect-information extensive-form games. The Recursive Belief-based Learning (ReBeL) framework already mitigates one source of training fragility by sampling the pivot iteration uniformly from the iteration budget; we identify a second, hitherto unaddressed source: the budget itself is held fixed across all subgames, creating a rigid coupling between solver maturity and outer-loop learning that propagates variance through the recursive self-play and produces noisy, seed-dependent training trajectories. We propose \textbf{Stochastic Horizon Annealing (SHA)}, which randomizes only this remaining static degree of freedom: at each subgame the total CFR iteration count is drawn from a Gaussian centered at the expected budget. Combined with ReBeL's existing uniform pivot, the procedure smooths the learning objective across a continuum of solving depths and behaves as an implicit ensemble at zero additional cost. SHA is a one-line change to any ReBeL-style trainer. We give a complete theoretical treatment with three results, all proved in the main text: (i) SHA preserves the $O(N^{-1/2})$ convergence rate of linear CFR; (ii) the per-subgame target variance is bounded by $C_\beta^2\sigma^2/(4N^3)$, vanishing rapidly with the budget; and (iii) the recursive variance of the value-network targets scales as $\Theta(D)$ for SHA versus $\Theta(D^2)$ for the fixed-horizon ReBeL, where $D$ is the recursion depth. On Liar's Dice 1$\times$4f, 1$\times$5f, and 1$\times$6f (30 seeds each) at the ReBeL reference setting of depth-2 subgames and 1024 search iterations, SHA reduces mean final exploitability by 9--18\% and shrinks the 95\% confidence interval across seeds by 34--63\%, with larger games benefiting more as predicted by the theory, establishing stability as a first-class, theoretically supported contribution for RL+Search on imperfect-information games.

NeurIPS 2026

Stabilizing Policy Optimization via Logits Convexity

Hongzhan Chen, Tao Yang, Yuhua Zhu, Shiping Gao, Xiaojun Quan, Ting Yao

While reinforcement learning (RL) has been central to the recent success of large language models (LLMs), RL optimization is notoriously unstable, especially when compared to supervised fine-tuning (SFT). In this work, we investigate the stability gap between SFT and RL from a gradient-based perspective, and show that the convexity of the SFT loss with respect to model logits plays a key role in enabling stable training. Our theoretical analysis demonstrates that this property induces favorable gradient directionality during optimization. In contrast, Proximal Policy Optimization (PPO), a widely adopted policy gradient algorithm utilizing a clipped surrogate objective, lacks this stabilizing property. Motivated by this observation, we propose Logits Convex Optimization (LCO), a simple yet effective policy optimization framework that aligns the learned policy with an optimal target derived from the original RL objective, thereby emulating the stabilizing effects of logits-level convexity. Extensive experiments across multiple model families show that our LCO framework consistently improves training stability and outperforms conventional RL methods on a broad range of benchmarks.

继续浏览

更多 AI 顶会论文

30+ 个顶会，按会议、年份和主题浏览。

浏览全部会议

进入任一会议和年份，查看完整论文列表。

全部会议 →

搜索论文

按标题、作者或关键词，在 21 万+ 篇论文里搜索。

搜索论文 →