论文检索

Social Aspects · Accountability, Transparency, and Interpretability

Tianlong Xu, Wang Zixiong, Lishuai Hou, Gaoyang Liu, Chen Wang, Xiaoyi Fan

In the pre-training-fine-tuning paradigm, pre-trained encoders have become high-value intellectual property (IP) due to their immense training costs, necessitating robust protection. Existing fingerprinting or watermarking methods typically rely on pre-defined samples and labels, or require intrusive modifications to the training process. However, downstream fine-tuning can significantly alter an encoder's representation and label space, thereby destroying the label consistency of existing methods and rendering them ineffective. Consequently, it is both challenging and urgent to provide a downstream-agnostic, black-box ownership verification mechanism for pre-trained encoders. To address this, we propose a downstream-agnostic, label-only fingerprinting method that leverages Adversarial Shifting to construct stable fingerprint clusters in the encoder’s latent space. By exploiting the inherent output consistency of these clusters, our method remains effective regardless of the specific downstream task or label mapping. Extensive experiments demonstrate that our method maintains superior robustness and stealthiness across various downstream tasks and category scales, providing a practical and reliable IP protection scheme for high-value pre-trained encoders.

General Machine Learning · Transfer, Multitask and Meta-learning

Rujikorn Charakorn, Edoardo Cetin, Shinnosuke Uesaka, Robert Lange

Long input sequences are central to in-context learning, document understanding, and multi-step reasoning of Large Language Models (LLMs). However, the quadratic attention cost of Transformers makes inference memory-intensive and slow. While context distillation (CD) can transfer information into model parameters, per-prompt distillation is impractical due to training costs and latency. To address these limitations, we propose Doc-to-LoRA (D2L), a lightweight hypernetwork that meta-learns to perform approximate CD within a single forward pass. Given an unseen prompt, D2L generates a LoRA adapter for a target LLM, enabling subsequent queries to be answered without re-consuming the original context, reducing latency and KV-cache memory consumption during inference of the target LLM. On a long-context needle-in-a-haystack task, D2L successfully learns to map contexts into adapters that store the needle information, achieving near-perfect zero-shot accuracy at sequence lengths exceeding the target LLM’s native context window by more than 4x. On real-world QA datasets with limited compute, D2L outperforms standard CD while significantly reducing peak memory consumption and update latency. We envision that D2L can facilitate rapid adaptation of LLMs, opening up the possibility of frequent knowledge updates and personalized chat behavior. Code and checkpoints will be released upon publication.

Xintong Yang, Hao Gu, Binxing Xu, Lujun Li, Bei Liu, Jiacheng Liu, Qiyuan Zhu, Sirui Han, Yike Guo

Large Language Models (LLMs) are increasingly expected to operate over long contexts, yet standard softmax attention incurs a KV cache that grows linearly with sequence length, quickly becoming the bottleneck for long context inference. A practical remedy is to evict less important KV entries; however, existing eviction policies are largely heuristic and struggle to capture the rich, input-dependent distribution of token importance. In this work, we introduce a **learnable indexer** that predicts KV importance, enabling more accurate retention of critical tokens. Meanwhile, naively evicting tokens permanently discards their information, leading to irreversible forgetting and degraded retrieval over long ranges. To address this, we propose a lightweight **latent memory module** that compresses evicted tokens into a compact, online-updated state and provides residual readouts to compensate for the attention contributions lost through KV eviction. Collectively, our method enables accurate long-context inference under a bounded KV budget, delivering consistent improvements on RULER (4K/16K) across Qwen, Mistral, and Llama models (up to 25 points under aggressive eviction), markedly more stable Needle-in-a-Haystack retrieval, and superior LongBench scores and compression curves compared to existing eviction policies.

Probabilistic Methods · Monte Carlo and Sampling Methods

Zonghao Chen, Toni Karvonen, Heishiro Kanagawa, Francois-Xavier Briol, Chris J Oates

Approximation of a target probability distribution using a finite set of points is a problem of fundamental importance in numerical integration. Several authors have proposed to select points by minimising a maximum mean discrepancy (MMD), but the non-convexity of this objective typically precludes global minimisation. Instead, we consider the concept of \emph{stationary points of the MMD} which, in contrast to points globally minimising the MMD, can be accurately computed. Our main contributions are two-fold and theoretical in nature. We first prove the (perhaps surprising) result that, for integrands in the associated reproducing kernel Hilbert space, the numerical integration error of stationary MMD points vanishes \emph{faster} than the MMD. Motivated by this \emph{super-convergence} property, we consider MMD gradient flows as a practical strategy for computing stationary points of the MMD. We then prove that MMD gradient flow can indeed compute stationary MMD points, based on a refined convergence analysis that establishes a novel non-asymptotic finite-particle error bound.

Deep Learning · Large Language Models

Rishi Sharma, Martijn de Vos, Pradyumna Chari, Ramesh Raskar, Anne-Marie Kermarrec

Collaborative agentic AI is projected to transform entire industries by enabling AI-powered agents to autonomously perceive, plan, and act within digital environments. Yet, current solutions in this field are all built in isolation, and we are rapidly heading toward a landscape of fragmented, incompatible ecosystems. In this position paper, we argue that interoperability, achieved by the adoption of minimal standards, is essential to ensure open, secure, web-scale, and widely-adopted agentic ecosystems. To this end, we devise a minimal architectural foundation for collaborative agentic AI, named Web of Agents, which is composed of four components: agent-to-agent messaging, interaction interoperability, state management, and agent discovery. Web of Agents adopts existing standards and reuses existing infrastructure where possible. With Web of Agents, we take a first but critical step toward interoperable agentic systems and offer a pragmatic path forward before ecosystem fragmentation becomes the norm.

Probabilistic Methods · Monte Carlo and Sampling Methods

Yihang Sun, Guanyang Wang, Jose Blanchet

We study the estimation of repeatedly nested expectations (RNEs) with a constant horizon (number of nestings) using quantum computing. We propose a quantum algorithm that achieves $\varepsilon$-error with cost $\tilde O(\varepsilon^{-1})$, up to logarithmic factors. Standard lower bounds show this scaling is essentially optimal, yielding an almost quadratic speedup over the best classical algorithm. Our results extend prior quantum speedups for single nested expectations to repeated nesting, and therefore cover a broader range of applications, including optimal stopping. This extension requires a new derandomized variant of the classical randomized Multilevel Monte Carlo (rMLMC) algorithm. Careful de-randomization is key to overcoming a variable-time issue that typically increases quantized versions of classical randomized algorithms.

Deep Learning · Theory

Mengqi Li, Wensheng Lin, Jinshuai Yang, Lixin Li

Effective sequence modeling fundamentally requires balancing the retention of unbounded history with the high-resolution detection of abrupt short-term variations common in real-world phenomena. However, existing state space models (SSMs) relying on high-order polynomial projection operators (HiPPO) face a critical trade-off where uniform measures dilute recent information to maintain timescale invariance, while exponential measures sacrifice global context to capture local dynamics. This paper proposes a Fractional Recurrent Architecture for Computational Temporal Analysis of Long sequences (FRACTAL), a novel architecture integrating fractional measure theory into recursive memory updates to address this limitation. By deriving projection operators with analytically characterized spectral properties and a tunable singularity index, the proposed method amplifies sensitivity to recent signal perturbations while preserving the spectral structure that encodes scale-invariant memory dynamics. This theoretical innovation is instantiated within a simplified diagonalized state space framework by modulating input projection initialization to enable simultaneous capture of multi-scale temporal features. FRACTAL achieves an average score of 87.11\% on the Long Range Arena benchmark, including 61.85\% on the ListOps task, outperforming the S5 model.

Deep Learning · Large Language Models

Ziyi Wang, Haonan Jin, Zian Wang, Wendong Wang, Lanshan Zhang

Small language models (SLMs) are attractive for agent deployment, but they struggle to reliably retain and reuse decision-relevant state information over long interactions. This issue is exacerbated when working memory is maintained via unstructured natural-language summarization. Some recent work addresses this limitation by fine-tuning or distilling smaller models to better construct and utilize working memory, but such approaches typically incur substantial additional training cost and require continuous data construction. We present a training-free working-memory framework for SLM-based agents that makes decision-relevant state explicit: conditioned on the active (sub)goal, the agent maintains a compact information state needed for progress assessment and the currently effective action set. Our approach decomposes tasks into subgoals and organizes memory hierarchically into task-level global memory and subtask-level local memory, where local memory directly conditions SLM action selection and is updated from new observations. To instantiate goal-conditioned memories without parameter updates, we introduce an offline LLM-based induction pipeline that builds a reusable schema once per task family from a small number of representative traces. Training-free refers to no parameter updates of the deployed SLM and no online LLM calls; we only use a one-time offline LLM-based schema induction per task family. On ALFWorld valid\_unseen, a 4B SLM achieves 0.910 success, while representative prompting and prior working-memory baselines under the same setting remain below 0.320.

Deep Learning · Everything Else

Haosen Wang, Jing Xiao, Mengqiao Li, Xuanze Wang, Mingzheng Zhang, Xiaowang Zhang, Zhiyong Feng

Precise evidence region localization in Document Visual Question Answering (DocVQA) is crucial for improving model interpretability and reliability. However, most existing approaches rely on single-step localization, which struggles to effectively distinguish true evidence from irrelevant content when page semantics are complex or evidence regions are extremely small, leading to ambiguous boundaries and localization errors. To address these challenges, we propose a progressive evidence localization framework based on Wasserstein gradient flows, which reformulates evidence localization as an optimal transport optimization problem over probability distributions. Since continuous-time gradient flows are intractable in practice, we adopt the Jordan--Kinderlehrer--Otto (JKO) scheme for discrete optimization and derive an end-to-end trainable loss function that translates the theoretical framework into a neural network–optimizable objective. This formulation enables precise evidence localization through progressive refinement from coarse-grained to fine-grained regions. Experimental results demonstrate that our method significantly outperforms existing approaches in both evidence localization and answer generation, while providing an interpretable progressive reasoning process.

Reinforcement Learning · Deep RL

Hao Wang, Lei Sha, Jie Zhang

Existing code reasoning methods primarily supervise final code outputs, ignoring intermediate states, often leading to reward hacking where correct answers are obtained through inconsistent reasoning. We propose StepCodeReasoner, a framework that introduces explicit intermediate execution-state supervision. By automatically inserting structured print-based execution-trace anchors into code, the model is trained to predict runtime states at each step, transforming code reasoning into a verifiable, stepwise execution modeling problem. Building on this execution-aware method, we introduce Bi-Level GRPO}, a reinforcement learning algorithm for structured credit assignment at two levels: inter-trajectory, comparing alternative execution paths, and intra-trajectory, rewarding intermediate accuracy based on its impact on downstream correctness. Extensive experiments demonstrate that StepCodeReasoner achieves SOTA performance in code reasoning. In particular, our 7B model achieves 91.1\% on CRUXEval and 86.5\% on LiveCodeBench, outperforming the CodeReasoner-7B baseline (86.0\% and 77.7\%) and GPT-4o (85.6\% and 75.1\%). Furthermore, on the execution-trace benchmark REval, our model scores 82.9\%, outperforming baseline CodeReasoner-7B (72.3\%), its 14B counterpart (81.1\%), and GPT-4o (77.3\%). Additionally, our approach also improves code generation performance, demonstrating that explicit execution modeling enhances both code reasoning and code generation.

Deep Learning · Generative Models and Autoencoders

Zihao Cheng, Binrui Wu, Yuesen Liao, Weizhong Zhang

Diffusion probabilistic models (DPMs)’ sampling process is often inefficient, requiring hundreds to thousands of iterative steps to accurately approximate the diffusion trajectory. This inefficiency limits their practical applicability. Although recent advances in sampling efficiency—such as numerical solvers for diffusion ordinary differential equations (ODEs)—have made progress, significant challenges remain: training-free numerical solvers suffer from the suboptimality of manually designed timestep selection rules and the inherent inconsistency between the forward diffusion process (typically involving thousands of steps) and the reverse denoising process (usually limited to tens of steps). Since timestep selection is inherently a discrete problem and cannot be optimized via gradients, we propose an innovative approach—reparameterizing the timestep scheduling through probabilistic masking, thereby enabling gradient-based optimization of sampling timesteps. To circumvent backpropagation, we employ policy gradient methods. Furthermore, to address the inconsistency between forward diffusion (training) and reverse denoising (inference), we extend this framework into a bilevel optimization paradigm: the inner loop performs additional lightweight training on the model at specific timesteps determined by the outer mask to align forward and reverse processes, while the outer loop optimizes the timestep distribution via probabilistic masking and policy gradient based on generation quality. Under mild assumptions, we theoretically analyze the convergence of the proposed algorithm. Extensive experiments across diverse datasets and samplers demonstrate that this framework effectively enhances sampling efficiency and generation quality while maintaining compatibility with various DPM architectures and advanced ODE solvers.

Social Aspects · Accountability, Transparency, and Interpretability

Sina Tayebati, Divake Kumar, Nastaran Darabi, Davide Ettori, Ranganath Krishnan, Amit Trivedi

Estimating uncertainty for AI agents in real-world multi-turn tool-using interaction with humans is difficult because failures are often triggered by sparse critical episodes (e.g., looping, incoherent tool use, or user-agent miscoordination) even when local generation appears confident. Existing uncertainty proxies focus on single-shot text generation and therefore miss these trajectory-level breakdown signals. We introduce TRACER, a trajectory-level uncertainty metric for dual-control Tool-Agent-User interaction. TRACER combines content-aware surprisal with situational-awareness signals, semantic and lexical repetition, and tool-grounded coherence gaps, and aggregates them using a tail-focused risk functional with a MAX-composite step risk to surface decisive anomalies. We evaluate TRACER on $\tau^2$-bench (Barres et al., 2025) by predicting task failure and selective task execution. To this end, TRACER improves AUROC by up to 37.1\% and AUARC by up to 55\% over baselines, enabling earlier and more accurate detection of uncertainty in complex conversational tool-use settings.

Probabilistic Methods · Monte Carlo and Sampling Methods

Xiaotong Ji, Rasul Tutunov, Matthieu Zimmer, Haitham Bou Ammar

Reinforcement learning (RL) post-training is a dominant approach for improving the reasoning performance of large language models (LLMs), yet growing evidence suggests that its gains arise primarily from distribution sharpening rather than the acquisition of new capabilities. Recent work has shown that sampling from the power distribution of LLMs using Markov chain Monte Carlo (MCMC) can recover performance comparable to RL post-training without relying on external rewards; however, the high computational cost of MCMC makes such approaches impractical for widespread adoption. In this work, we propose a theoretically grounded alternative that eliminates the need for iterative MCMC. We derive a novel formulation showing that the global power distribution can be approximated by a token-level scaled low-temperature one, where the scaling factor captures future trajectory quality. Leveraging this insight, we introduce a training-free and verifier-free algorithm that sharpens the base model's generative distribution autoregressively. Empirically, we evaluate our method on math, QA, and code tasks across four LLMs, and show that our method matches or surpasses one-shot GRPO without relying on any external rewards, while reducing inference latency by over $10\times$ compared to MCMC-based sampling.

Applications · Health / Medicine

Josh Sun, Morteza Babaie, Wenyang hou, Mark Crowley, David Young

Antibody expression ranking is a critical task in antibody design, yet its modeling is severely hindered by the scarcity of labeled experimental data. To address this, we propose a unified preference-based learning framework that integrates scarce quantitative expression data with large-scale weak positive supervision from immunization data. We adapt Direct Preference Optimization (DPO) to protein language models by introducing a union-masked log-likelihood approximation and IMGT-based alignment, enabling efficient training on variable-length sequences. Evaluating on a diverse internal dataset of 1254 labeled sequences and 4 million unlabeled camelid-derived antibodies, we show that our method consistently outperforms baselines on most metrics. Our results demonstrate that preference learning can effectively learn from weak supervision, providing a scalable solution for antibody expressibility optimization in data-constrained settings.

Social Aspects · Accountability, Transparency, and Interpretability

Tianyi She, Jiawei Liu, Weifeng Liu, Hanqing Zhao, Weiming Zhang, Kejiang Chen

Recent advances in LipSync generation technology have led to the creation of highly realistic videos, posing severe societal risks. However, existing defense strategies struggle against LipSync forgeries, as state-of-the-art generative models not only optimize for the lip synchronization but also significantly eliminate visual artifacts, resulting in the lack of key detection signals. Inspired by the inherent biological coupling between lip movements and head poses in natural speech, we observe that generative models fundamentally disrupt this global coordination when optimizing for local lip motion. In this paper, we propose LipDA, a novel framework for joint LipSync Detection and Attribution, which takes advantage of the inconsistency between head and lip. For detection, the framework learns to quantify this discrepancy by contrasting lip and pose features from authentic versus forged videos. For attribution, our method is designed to capture the unique temporal dynamics and audio-visual synchronization patterns that act as generative fingerprints, enabling source tracing. To validate our approach, we conduct extensive experiments on two challenging LipSync benchmarks as well as on our own proposed large-scale and multi-generator dataset, LipSyncBench-A. LipDA achieves over 97% AUC in detection and 97.5% accuracy in model attribution, significantly outperforming existing methods.

Micah Adler

We study the capacity of the self-attention key-query channel: for a fixed budget, how many distinct token-token relations can a single layer reliably encode? We introduce *Relational Graph Recognition*, where the key-query channel encodes a directed graph and, given a context (a subset of the vertices), must recover the neighbors of each vertex in the context. We measure resources by the total key dimension $D_K = hd_k$. In a tractable multi-head model, we prove matching information-theoretic lower bounds and upper bounds via explicit constructions showing that recovering a graph with $m'$ relations in $d_{\text{model}}$-dimensional embeddings requires $D_K$ to grow essentially as $m'/d_{\text{model}}$ up to logarithmic factors, and we obtain corresponding guarantees for scaled-softmax attention. This analysis yields a new, capacity-based rationale for multi-head attention: even in permutation graphs, where **all queries attend to a single target**, splitting a fixed $D_K$ budget into multiple heads increases capacity by reducing interference from embedding superposition. Controlled experiments mirror the theory, revealing sharp phase transitions at the predicted capacity, and the multi-head advantage persists when adding softmax normalization, value routing, and a full Transformer block trained with frozen GPT-2 embeddings.

Probabilistic Methods · Monte Carlo and Sampling Methods

Bin Yang, Xiaojie Wang

Sampling from a high-dimensional probability distribution is a fundamental algorithmic task arising in wide-ranging applications across multiple disciplines, including scientific computing, computational statistics and machine learning. Langevin Monte Carlo (LMC) algorithms are among the most widely used sampling methods in high dimensional settings. This paper introduces a novel higher-order and Hessian-free LMC sampling algorithm based on an efficient stochastic Runge-Kutta method of strong order $1.5$ for the overdamped Langevin dynamics. In contrast to the existing Runge-Kutta type LMC (Li et al.,2019) involved with three gradient evaluations, the newly proposed algorithm is computationally cheaper and requires only two gradient evaluations for one iteration. Under certain log-smooth conditions, non-asymptotic error bounds of the proposed algorithms are analyzed in $\mathcal{W}_2$-distance. In particular, a uniform-in-time convergence rate of order $O(d ^{\frac32} h^{\frac32})$ is derived in a non-log-concave setting, matching the convergence rate proved in the aforementioned work but under the log-concavity condition. Numerical experiments are finally presented to demonstrate the effectiveness of the new sampling algorithm.

Deep Learning · Large Language Models

Yi-Kai Zhang, Zhiyuan Yao, Hongyan Hao, Yueqing Sun, Qi GU, Hui Su, Xunliang Cai, De-Chuan Zhan, Han-Jia Ye

Traditional value models $V^{\pi}$ in LLM reinforcement learning face a coupling dilemma: they require synchronous training alongside the updating policy $\pi$, causing inefficiency and overfitting. In this paper, we propose $V_0$, a generalist value model that decouples value estimation from specific policy parameters by reframing the task as in-context learning to predict performance for unseen policies. We utilize the policy's historical query-performance pairs as a capability representation, transforming from $V^{\pi}(s_0)$ to $V(C_{\pi}, s_0)$, where $C_{\pi}$ serves as an in-context input. This architecture enables us to scale the diversity of policies within the training set. Consequently, $V_0$ achieves scaling in learning to rapidly identify the capability boundaries of any policy without updating its parameters. Technically, we employ a Residual Query Adapter to compress the high-dimensional policy representation and the target query into structured features, which are then processed by a pre-trained TabPFN head. Empirical results show that $V_0$ outperforms coupled value models in tracking policy evolution during GRPO training, optimizes cold-start budget allocation, and approaches the performance-cost Pareto frontier in inference routing.

Deep Learning · Large Language Models

Feng Zhao, Hong Zhang, Yu Yang, Ruilin Zhao, Guandong Xu

Supervised fine-tuning (SFT) is central to aligning large language models (LLMs) with instruction following and task-specific reasoning. Despite its success, SFT optimizes token-level likelihoods under the implicit assumption that strictly fitting all tokens in expert demonstrations induces the desired downstream behavior. However, in reasoning tasks where correctness is defined by logical validity or final outcomes rather than exact token realizations, this assumption can lead to optimization misalignment. We empirically observe that low-probability tokens in reasoning demonstrations often correspond to realization-specific or stylistic variations, and that reducing their influence during training consistently improves generalization on reasoning benchmarks. Motivated by this insight, we propose the *Bounded Log-Likelihood Loss* (BLL-Loss), a simple and parameter-free alternative to standard likelihood training that bounds gradient contributions from low-probability tokens while preserving conventional optimization behavior. We provide theoretical insights and extensive empirical results demonstrating that BLL-Loss improves reasoning generalization across diverse model scales and challenging benchmarks.

Deep Learning · Graph Neural Networks

James Flora, Mitchell Black, Weng-Keen Wong, Amir Nayyeri

Positional encodings (PEs) enhance the power of graph neural networks (GNNs), both theoretically and empirically. Two of the most popular families of PEs---spectral (e.g., Laplacian eigenspaces, effective resistance) and random walk (polynomials of the adjacency matrix)---are theoretically equivalent in expressive power, and both are known to lie between the 1-WL and 3-WL tests in terms of expressivity. However, this equivalence assumes the GNN uses the "complete'' version of these PEs, which requires $O(n^3)$ time and space complexity. Practitioners therefore commonly use truncated variants of these encodings (e.g., the first $k$ eigenspaces or powers of adjacency matrix). However, the theoretical properties of these truncated PEs are unknown. In this work, we initiate the study of these truncated PEs. Theoretically, we show that, under truncation, several families of PEs are fundamentally different in expressive power. As a corollary, we show that truncated spectral PEs are no longer stronger than the 1-WL test. We also study a family of spectral PEs, the $k$-harmonic distances, to highlight the differences in expressive power of even closely related truncated PEs. Finally, we experimentally show that a mix of truncated PEs is preferable to any single family on real-world datasets.