论文检索

Applications · Everything Else

Steven Xia, Minbiao Han, Jonathan Li, Raul Castro Fernandez, Haifeng Xu, sainyam galhotra

Data markets promise to unlock data value by matching data suppliers with ML consumers. However, market design involves addressing intricate challenges, including data pricing, fairness, and robustness. We propose a pragmatic data-augmented AutoML market that seamlessly integrates with existing cloud-based AutoML platforms, such as Google’s Vertex AI. Unlike standard AutoML solutions, our design automatically augments buyer-submitted training data with valuable external datasets, pricing the resulting models based on their measurable performance improvements rather than computational costs as the status quo. Our key innovation is a pricing mechanism grounded in the instrumental value—the marginal model quality improvement—of externally sourced data. This approach bypasses direct dataset pricing complexities and accommodates diverse buyer valuations through menu-based options, thus providing an economically sustainable framework for monetizing external data.

Deep Learning · Large Language Models

Zejia You, Chunyuan Deng, Hanjie Chen

Inference-time steering has emerged as a promising paradigm for controlling language models (LMs) without the cost of retraining. However, standard approaches typically rely on activation addition, a geometric operation that inevitably alters the magnitude of hidden representations. This raises concerns about representation collapse and degradation of open-ended generation capabilities. In this work, we explore Spherical Steering, a training-free primitive that resolves this trade-off through activation rotation. Rather than shifting activations with a fixed vector, our method rotates them along a geodesic toward a target direction, guiding the activation toward the target concept while preserving the integrity of the signal. To further enhance adaptivity, we incorporate a confidence gate that dynamically modulates steering strength based on input uncertainty. Extensive experiments across multiple-choice benchmarks demonstrate that Spherical Steering significantly outperforms addition-based baselines (notably by +10\% on TruthfulQA, COPA, and Storycloze), while simultaneously maintaining the model’s general open-ended generation quality. This work highlights the value of geometric consistency, suggesting that norm-preserving rotation is a robust and effective primitive for precise inference-time control.

Reinforcement Learning · Everything Else

Zeyu Zhao, Yueling Che, Kaichen Liu, Jian Li, Junmei Yao

Multi-objective reinforcement learning (MORL) is a fundamental framework for real-world decision-making problems involving multiple conflicting criteria. Existing multi-policy (MP) methods typically rely on online evolutionary frameworks that maintain large policy populations, leading to high sample complexity and excessive agent–environment interactions. To mitigate these limitations, we present Multi-policy Pareto Front Tracking (MPFT), a framework without a self-evolving population. It leverages an efficient Pareto-tracking mechanism initialized with single-objective extreme policies to trace the Pareto front, and further densifies sparse regions to achieve an accurate approximation of the full Pareto front. MPFT can be seamlessly integrated with advanced offline MORL algorithms, thereby substantially improving sample efficiency. We evaluate MPFT on six robotic control tasks with up to three objectives and three high-dimensional tasks with more than three objectives. Experimental results show that MPFT outperforms state-of-the-art baselines in terms of hypervolume and expected utility. It also significantly reduces agent–environment interactions. These results further demonstrate that MPFT serves as a general-purpose framework that can seamlessly integrate both online and offline MORL algorithms.

Applications · Health / Medicine

Pengkai Wang, Pengwei Liu, Qi Zuo, Zhijie Sang, Congkai Xie, Hongxia Yang

Reinforcement learning (RL) has powered many of the recent breakthroughs in large language models (LLMs), especially for tasks where rewards can be computed automatically, such as code generation. However, these methods deteriorate in open-ended domains like medical consultation, where feedback is inherently ambiguous, highly context-dependent, and cannot be reduced to a reliable scalar signal. In such settings, RL must either rely on supervision-intensive reward models that often fail to generalize, or it falls into pathological behaviors such as reward hacking—an especially troubling risk for high-stakes medical dialogue. To address these limitations, we introduce ORBIT, an open-ended rubric-based incremental training framework for high-stakes medical dialogue. ORBIT integrates synthetic dialogue generation with dynamically constructed rubrics that serve as adaptive guides for incremental RL. Instead of relying on external medical knowledge bases or handcrafted rule sets, ORBIT uses rubric-driven feedback to steer the learning process. Its judge component can be instantiated with general-purpose instruction-following LLMs, removing the need for any task-specific fine-tuning. Applied to the Qwen3-4B-Instruct model, ORBIT raises the HealthBench-Hard score from 7.0 to 27.5 using only 2k training samples, achieving SOTA performance for models at this scale. With larger rubric datasets, ORBIT-trained models further compete with the strongest open-source baselines on HealthBench-Hard. Our analysis shows that rubric-guided RL consistently improves consultation quality across diverse medical scenarios. We also apply such rubric generation and training pipeline to InfoBench, where ORBIT enhances instruction-following performance, highlighting the generality of rubric-based feedback.

Deep Learning · Generative Models and Autoencoders

Muyu Wang, Xingping Dong, Jianzhe Gao, Wenguan Wang, Yujia Wang

Despite rapid progress in 3D generative models, producing production-grade 3D face assets from a single image remains challenging. To reconstruct facial micro-structures and fine-grained multiview-consistent textures, this work presents a two-stage framework named SAMT for monocular 3D avatar generation and texture synthesis. Specifically, a latent 3D diffusion model for facial mesh generation is pretrained and then further adapted to generate high-quality facial geometry through large-scale domain-specific fine-tuning on 35K curated 3D avatar models. Subsequently, a multiview-aware texturing strategy is proposed to texture the generated facial mesh. Its core idea lies in incorporating a multi-view facial prior, along with mesh geometry, to guide a 2D texturing diffusion for cross-view consistent and mesh-aligned texture synthesis. Extensive experiments demonstrate that SAMT outperforms existing approaches by producing more structured and detailed facial geometry, along with improved fine-grained appearance coherence.

Deep Learning · Large Language Models

Wenhao Gao, Haoran Cao, Yueyan Li, YongGao Xiao, Caixia Yuan, Xiaojie Wang

The prohibitive memory footprint of the Key-Value (KV) cache imposes a critical bottleneck for efficient long-context LLM serving. Current compression techniques typically rely on static or uniform budget allocation, overlooking the significant heterogeneity in information density across attention heads. To address this, we introduce \textsc{EntroKV}, an entropy-driven dynamic budget allocation framework. Our method enables dynamic and rational allocation across layers, attention heads, and different tasks. We demonstrate that attention entropy serves as a robust proxy for compression sensitivity: heads with high entropy require larger retention budgets, whereas low-entropy heads can be aggressively compressed without accuracy degradation. Functioning as a lightweight, plug-and-play module, \textsc{EntroKV} optimizes budget scheduling in real-time and is compatible with diverse compression operators. Extensive experiments demonstrate that \textsc{EntroKV} consistently outperforms baselines, retaining $\sim$98\% of full-cache performance at a 30\% budget ratio with negligible computational overhead. Our code is available at \url{https://anonymous.4open.science/r/EntroKV-D0C8/}.

Deep Learning · Large Language Models

Kaixiang Wang, Yidan Lin, Jiong Lou, Zihan Wang, Bunyod Suvonov, Zhaojiacheng Zhou, Yuxiang Zheng, Jiaxi Cao, Zhiheng Dong, Chentao Wu 等

The evolution of Large Language Model (LLM) agents towards System~2 reasoning, characterized by deliberative, high-precision problem-solving, necessitates maintaining rigorous logical integrity over extended horizons. However, prevalent memory preprocessing paradigms incur destructive de-contextualization. By compressing fluid sequential dependencies into pre-defined structures (e.g., embeddings or graphs), these methods sever the narrative integrity essential for deep reasoning. To address this, we propose E-mem, a framework shifting from Memory Preprocessing to Episodic Context Reconstruction inspired by biological engrams. E-mem employs a heterogeneous hierarchical architecture where multiple assistant agents maintain uncompressed memory contexts, while a central master agent orchestrates global planning. Unlike passive retrieval, our mechanism empowers assistants to locally reason within activated segments, extracting context-aware evidence before aggregation. Evaluations on the LoCoMo benchmark demonstrate that E-mem achieves over 54\% F1—surpassing the state-of-the-art GAM by 7.75\%—while reducing token cost by over 70\%. Our work is available on \url{https://anonymous.4open.science/r/E-mem-F6C3/}.

Reinforcement Learning · Online

Chubin Zhang, Zhenglin Wan, Feng Chen, Fuchao Yang, Lang Feng, Yaxin Zhou, Xingrui Yu, Yang You, Ivor Tsang, Bo An

Reinforcement learning (RL) faces a persistent tension: policies that are stable to optimize (e.g., Gaussians) are often too simple to represent the multimodal action distributions required for complex control. Conversely, expressive generative policies—such as diffusion and flow matching—are frequently unstable in online RL due to intractable likelihoods and gradients propagating through long sampling chains. We address this tension with a key structural principle: decoupling optimization from generation. Building on this, we introduce GoRL (Generative Online Reinforcement Learning), an algorithm-agnostic framework that trains expressive policies from scratch by confining policy optimization to a tractable latent space while delegating action synthesis to a conditional generative decoder. Using a two-timescale alternating schedule and anchoring decoder refinement to a fixed prior, GoRL enables stable optimization while continuously expanding expressiveness. Empirically, GoRL consistently outperforms unimodal and generative baselines across diverse continuous-control tasks. Notably, on the challenging HopperStand task, it achieves episodic returns exceeding 870—more than $3\times$ that of the strongest baseline—demonstrating a practical path to policies that are both stable and highly expressive.

General Machine Learning · Representation Learning

Diogo Soares, Pankhil Gawade, Andrea Dittadi, Ewa Szczurek

Evaluating representation similarity is fundamental to representation learning. However, existing metrics suffer from significant limitations: they are difficult to interpret due to shifting baselines, lack robustness to outliers, and are frequently computationally intractable for large datasets, forcing a reliance on heuristic approximations. To address these shortcomings, we develop an ordinal-similarity framework, instantiated by the Triplet (TSI) and Quadruplet (QSI) Similarity Indices, which measure alignment by quantifying the consistency of ordinal relationships. We provide a theoretical analysis demonstrating that this formulation is inherently interpretable, robust to outliers, and computationally efficient. Finally, we establish a formal equivalence between TSI alignment and the alignment of local neighborhood structures, as measured by Mutual Nearest Neighbors. Through empirical analysis, we validate these properties and show that ordinal similarity offers a scalable, practical approach to measuring alignment, enabling practitioners to better understand and design representations.

Applications · Language, Speech and Dialog

Yiqing Xie, Emmy Liu, Gaokai Zhang, Nachiket Kotalwar, Shubham Gandhi, Acharya, Xingyao Wang, Carolyn Rose, Graham Neubig, Daniel Fried

Coding agents are increasingly used for a wide range of real-world tasks, from adding features and documentation to creating programs from scratch. Ideally, the agent should perform well across all the diverse tasks. However, most prior work concentrates on issue solving, and such single-task training does not transfer reliably to other coding tasks. In this work, we aim to train coding agents that generalize across tasks. We first analyze task transferability from two axes: the commonalities shared among coding tasks and the capabilities of current agents. Guided by these findings, we derive a set of principles for training task design and verify them through a series of controlled experiments. We then present Hybrid-Gym, a training dataset built on four scalable training tasks that follow these principles. Experiments show that, under zero-shot task transfer, Hybrid-Gym achieves performance comparable to in-domain training, and further improves existing datasets when combined with them (e.g., +4.85% on SWT-Bench-Verified).

Applications · Computer Vision

Ruihang Li, Mengde Xu, Shuyang Gu, Leigang Qu, Fuli Feng, Han Hu, Wenjie Wang

Conventional reinforcement learning strategies for visual generation typically employ sample-wise reward functions, yet this practice frequently results in reward hacking that degrades image diversity and introduces visual anomalies. To address these limitations, we present a novel framework that finetunes generative models using distribution-wise rewards, ensuring better alignment with real-world data distributions. Unlike rewards that evaluate samples individually, distribution-wise reward accounts for the data distribution of the samples, mitigating the mode collapse problem that occurs when all samples optimize towards the same direction independently. To overcome the prohibitive computational cost of estimating these rewards, we introduce a subset-replace strategy that efficiently provides reward signals by updating only a small subset of a generated reference set. Additionally, we apply RL to optimize post-hoc model merging coefficients, potentially mitigating the train-inference inconsistency caused by introducing stochastic differential equation (SDE) in regular RL practices. Extensive experiments show our approach significantly improves FID-50K across various base models, from 8.30 to 5.77 for SiT and from 3.74 to 3.52 for EDM2. Qualitative evaluation also confirms that our method enhances perceptual quality while preserving sample diversity.

Emmy Liu, Graham Neubig, Chenyan Xiong

Midtraining, the practice of mixing specialized data with more general pretraining data in an intermediate training phase, has become widespread in language model development, yet there is little understanding of what makes it effective. We propose that midtraining functions as distributional bridging by providing better initialization for posttraining. We conduct controlled pretraining experiments, and find that midtraining benefits are largest for domains distant from general pretraining data, such as code and math, and scale with the proximity advantage the midtraining data provides toward the target distribution. In these domains, midtraining consistently outperforms continued pretraining on specialized data alone both in-domain and in terms of mitigating forgetting. We further conduct an investigation on the starting time and mixture weight of midtraining data, using code as a case study, and find that time of introduction and mixture weight interact strongly such that early introduction of specialized data is amenable to high mixture weights, while late introduction requires lower ones. This suggests that late introduction of specialized data outside a plasticity window cannot be compensated for by increasing data mixtures later in training. Beyond midtraining itself, this suggests that distributional transitions between any training phases may benefit from similar bridging strategies.

Social Aspects · Accountability, Transparency, and Interpretability

Emmy Liu, Varun Prashant Gangal, Chelsea Zou, Michael Yu, Xiaoqi Huang, Alex Chang, Zhuofu Tao, Karanpartap Singh, Sachin Kumar, Steven Feng

Despite numerous attempts at mitigation since the inception of language models, hallucinations remain a persistent problem even in today's frontier LLMs. Why is this? We review existing definitions of hallucination and fold them into a single, unified definition wherein prior definitions are subsumed. This position paper argues that hallucination can be unified by defining it as simply inaccurate (internal) world modeling, in a form where it is observable to the user. For example, stating a fact which contradicts a knowledge base OR producing a summary which contradicts the source. By varying the reference world model and conflict policy, our framework unifies prior definitions. We argue that this unified view is useful because it forces evaluations to clarify their assumed reference "world", distinguishes true hallucinations from planning or reward errors, and provides a common language for comparison across benchmarks and discussion of mitigation strategies. Building on this definition, we outline plans for a family of benchmarks using synthetic, fully specified reference world models to stress-test and improve world modeling components.

Deep Learning · Large Language Models

Emmy Liu, Graham Neubig, Chenyan Xiong

Midtraining, the practice of mixing specialized data with more general pretraining data in an intermediate training phase, has become widespread in language model development, yet there is little understanding of what makes it effective. We propose that midtraining functions as distributional bridging by providing better initialization for posttraining. We conduct controlled pretraining experiments, and find that midtraining benefits are largest for domains distant from general pretraining data, such as code and math, and scale with the proximity advantage the midtraining data provides toward the target distribution. In these domains, midtraining consistently outperforms continued pretraining on specialized data alone both in-domain and in terms of mitigating forgetting. We further conduct an investigation on the starting time and mixture weight of midtraining data, using code as a case study, and find that time of introduction and mixture weight interact strongly such that early introduction of specialized data is amenable to high mixture weights, while late introduction requires lower ones. This suggests that late introduction of specialized data outside a plasticity window cannot be compensated for by increasing data mixtures later in training. Beyond midtraining itself, this suggests that distributional transitions between any training phases may benefit from similar bridging strategies.

Deep Learning · Generative Models and Autoencoders

Zhongwei Zhang, Fuchen Long, Wei Li, Zhaofan Qiu, Wu Liu, Ting Yao, Tao Mei

The In-context generation paradigm has demonstrated strong power in instructional image editing for better synthesis quality. Nevertheless, shaping such in-context learning for instructional video editing is not trivial. Without specifying editing regions, the results can suffer from the issue of inaccurate editing regions and the token interference between different areas. To address these, we present ReCo, a new instructional video editing paradigm that novelly delves into **Re**gional **Co**nstraint modeling between editing and non-editing areas. Technically, ReCo width-wise concatenates source and target video for joint denoising. In model training, ReCo formulates regional constraints with two regularization terms, i.e., latent and attention regularization, on one-step backward denoised latents and attention maps, respectively. The former increases the latent discrepancy of the editing region between source and target videos while reducing that of non-editing areas, emphasizing editing area modification and alleviating unexpected content generation. The latter suppresses the attention of tokens in the editing region to the tokens in counterpart of the source video, thereby mitigating their interference during novel object generation in target video. Furthermore, we propose a large-scale, high-quality video editing dataset, i.e., ReCo-Data, comprising 500K instruction-video pairs. Extensive experiments conducted on four major instruction-based video editing tasks verify the superiority of ReCo.

Applications · Everything Else

Hanyang Wang, Xiwei Wu, Qinxiang Cao

Formal verification of system software with complex heap manipulations remains challenging. Standard automated solvers frequently fail to discharge separation logic verification conditions even when correct specifications like loop invariants are provided, forcing verification engineers to manually construct proofs. While large language models (LLMs) have shown promise in proof synthesis, specialized approaches for separation logic remain unexplored. To bridge this gap, we introduce SL-VC (Separation Logic Verification Conditions), a benchmark of 208 verification conditions derived from real-world C programs, including data structures and algorithms, the LiteOS kernel's linked list library, and the mini-gmp library. Our evaluation reveals that general-purpose LLMs and existing LLM-based Rocq provers struggle to effectively discharge these verification conditions. To address this challenge, we propose SPLIT (Split spatial and pure Proving with LLM-frIendly Tactics), a novel framework that enables predictable proof state transitions through an LLM-friendly tactic library, combined with a two-stage workflow that separates spatial and pure reasoning to align with separation logic semantics. Experimental results on SL-VC demonstrate that SPLIT consistently outperforms existing approaches, showing that LLM-assisted proof synthesis is a promising solution for separation logic verification of real-world system software.

Applications · Computer Vision

Jingxuan Wu, Zhenglin Wan, Xingrui Yu, Yuzhe YANG, Bo An, Ivor Tsang, Yang You

Flow-based text-to-image models follow deterministic trajectories, making it costly to explore diverse modes under limited sampling budgets. Existing approaches to improving diversity often rely on retraining or degrade image fidelity. To address this limitation, we present a training-free, inference-time control mechanism that makes the flow itself diversity-aware. Our core insight is to encourage diversity through guidance that is geometrically decoupled from the model’s quality-seeking direction. Our method simultaneously encourages lateral spread among trajectories via a feature-space objective and reintroduces uncertainty through a time-scheduled stochastic perturbation. Crucially, this perturbation is projected to be orthogonal to the generation flow, a geometric constraint that allows it to boost variation without degrading image details or prompt fidelity. Theoretically, we show that this design monotonically increases a volume surrogate while approximately preserving the marginal distribution, providing a principled explanation for the robustness of generation quality. Empirically, across multiple text-to-image settings under fixed sampling budgets, our method consistently improves diversity metrics such as the Vendi Score and Brisque over strong baselines, while upholding image quality and alignment.

Reinforcement Learning · Everything Else

Zhenglin Wan, Jingxuan Wu, Xingrui Yu, Chubin Zhang, Mingcong Lei, Bo An, Ivor Tsang, Yang You

Flow Matching (FM) has shown remarkable ability in modeling complex distributions and achieves strong performance in offline imitation learning for cloning expert behaviors. However, despite its behavioral cloning expressiveness, FM-based policies are inherently limited by their lack of environmental interaction and exploration. This leads to poor generalization in unseen scenarios beyond the expert demonstrations, underscoring the necessity of online interaction with environment. Unfortunately, optimizing FM policies via online interaction is challenging and inefficient due to instability in gradient computation and high inference costs. To address these issues, we propose to let a "student'' policy with simple MLP structure to explore the environment and be online updated via RL algorithm with a reward model. This reward model is associated with a "teacher'' FM model, containing rich information of expert data distribution. Furthermore, the same "teacher'' FM model is utilized to regularize the "student'' policy's behavior to stabilize policy learning. Due to the student’s simple architecture, we avoid the gradient instability of FM policies and enable efficient online exploration, while still leveraging the expressiveness of the teacher FM model. Extensive experiments shows that our approach significantly enhances learning efficiency, generalization, and robustness, especially when learning from suboptimal expert data.

Social Aspects · Fairness

Nika Haghtalab, Ariel Procaccia, Han Shao, Serena Wang, Kunhe Yang

Recent leaderboard-based evaluations of large language models aggregate user feedback by fitting a Bradley--Terry model to pairwise comparisons, producing a single global ranking based on a latent quality score. While appealing for its simplicity, this approach is incompatible with heterogeneous preferences: when LLMs are used across diverse tasks and use cases, users who favor fundamentally different model behaviors can be systematically misrepresented when collapsed into a single quality score. To address this issue, we study *pluralistic leaderboards* that aim to remain *stable* with respect to heterogeneous user populations. Drawing on ideas from social choice theory, we adapt the notion of *local stability*, which requires that no model outside the top-$k$ positions is collectively preferred to the top-$k$ set by more than $O(1/k)$ fraction of users. Building on techniques from the social choice literature, we design an alternative leaderboard mechanism that satisfies local stability while eliciting only $\widetilde{O}(k)$ pairwise comparisons per user, where $k$ is the size of the prefix for which stability is guaranteed. Using data from LMArena, we show that standard Bradley--Terry aggregation can violate local stability in practice, whereas our method provides substantially stronger stability guarantees.

Reinforcement Learning · Online

Qingzhang Zeng, Peixi Peng, hang li, Luntong Li, Yonghong Tian

Sample efficiency remains one of the central challenges in modern deep reinforcement learning (DRL). In recent years, world model approaches have significantly improved the sample efficiency of model-based reinforcement learning (MBRL) by enabling policy learning in imagination, thereby reducing the need for direct interaction with the real environment. However, most existing world model methods are trained independently for each task or perform multi-task learning in offline settings, failing to fully exploit the latent relationships among tasks in online interactive scenarios. To address this limitation, we propose TaskLoom, a knowledge-sharing world model architecture for online reinforcement learning. TaskLoom adopts a grouped two-stage training paradigm: in the first stage, fine-grained knowledge is shared among tasks within each group, while in the second stage, coarse-grained knowledge is exchanged across groups, enabling hierarchical knowledge transfer and reuse. Experimental results show that TaskLoom outperforms baseline methods on widely used benchmarks such as Proprio Control and Visual Control, validating the effectiveness of the proposed knowledge-sharing mechanism for both low-dimensional state and high-dimensional visual inputs.