论文检索

Deep Learning · Large Language Models

Yanlin Qi, Xinhang Chen, Huiqiang Jiang, Qitong Wang, Botao Peng, Themis Palpanas

KV-cache retrieval is essential for long-context LLM inference, yet existing methods struggle with distribution drift and high latency at scale. We introduce **ParisKV**, a drift-robust, GPU-native KV-cache retrieval framework based on collision-based candidate selection, followed by a quantized inner-product reranking estimator. For million-token contexts, ParisKV supports CPU-offloaded KV caches via Unified Virtual Addressing (UVA), enabling on-demand top-*k* fetching with minimal overhead. ParisKV matches or outperforms full-attention quality on both **long-input** and **long-generation** benchmarks. It achieves state-of-the-art long-context decoding efficiency: it matches or exceeds full-attention speed even at batch size 1 for long contexts, delivers up to **2.8×** higher throughput within full attention’s runnable range, and scales to **million-token** contexts where full attention runs out of memory. At million-token scale, ParisKV reduces decode latency by **17×** and **44×** compared to MagicPIG and PQCache, respectively—two state-of-the-art KV-cache top-*k* retrieval baselines.

Applications · Computer Vision

Shibo Lv, Jianmin Jiang

With the rapid development of deep learning, the issue of data scarcity has become increasingly prominent, inspiring emerging interests towards research on data augmentation techniques over recent years. However, our literature survey indicates that existing efforts often suffer from two issues of semantic infidelity, including: (i) visual semantics infidelity, such as visual artifacts, manifold intrusion, and unnatural blending boundaries etc, and (ii) label semantic infidelity, where augmented images do not match the original labels, creating extra label noises. To address these issues, we propose a Semantics Calibrated and Diffusion-Enhanced Augmentation (SCalDA) scheme to achieve accurate semantics calibration across image, label and feature domains. Compared with the existing approaches, our proposed features in precise guidance in label domain, semantics driven synthesis across three domains (image, label and feature), and semantics-aware metric learning. Extensive experiments on multiple datasets demonstrate that SCalDA yields consistent and significant performance improvements for both fine-grained and general classification tasks, validating the effectiveness and broad applicability of the proposed.

Applications · Chemistry, Physics, and Earth Sciences

Zeyu Wang, Xin Zheng, Yao Lu, Shanqing Yu, Qi Xuan, Shirui Pan

Few-shot molecular property prediction (FSMPP) is essential in drug discovery and materials design, where high-quality labeled data are often scarce and expensive to obtain. Despite the promising performance of existing methods, especially in the context-aware methods, they still face two-fold severe challenges with \textit{insufficient structural context modeling} \& \textit{redundant auxiliary context learning}, leading to inadequate context graph exploration and ineffective information utilization for effective molecule representation learning. To address these, in this paper, we propose a novel framework by learning on \textbf{\underline{Re}}lational and \textbf{\underline{C}}ompact c\textbf{\underline{o}}ntext \textbf{\underline{G}}raph, named \textbf{\method}, to comprehensively exploit the context graph for expressive molecular property prediction. Specifically, the proposed \method contains two core modules: a \textbf{(1) cross-property relational learning module} to better model the structural and relational context information, and a \textbf{(2) context graph information bottleneck module} to adaptively suppress irrelevant auxiliary signals for compact context information utilization, followed by a detailed theoretical demonstration regarding the importance of joint relational and compact knowledge extraction in context graphs. Extensive experiments across multiple datasets demonstrate that \method consistently outperforms state-of-the-art methods, validating its superiority. Code is available at~\url{https://anonymous.4open.science/r/ReCoG-main-40C7/}.

Yunchao Zhang, Yijia Weng, Ruizhe Liu, Ming Hu, Leonidas Guibas, Yanchao Yang

Learning motion latents for robotic manipulation heavily relies on extracting motion patterns from visual sequences, yet effective action abstractions require understanding three-dimensional geometric transformations. Here, we introduce GeoMoLa (Geometry-Aware Motion Latents), which learns discrete motion latent codes by predicting how point clouds evolve during manipulation rather than reconstructing visual observations. This four-dimensional objective – spatial geometry changing through time – forces latent representations to encode actual physical motion rather than appearance patterns. GeoMoLa achieves state-of-the-art performance using only single-view RGB-D input, while existing methods require multi-view reconstruction, succeeding across diverse manipulation benchmarks. Our ablations reveal that geometric prediction is the key to driving performance, quantitatively validating that manipulation depends on spatial understanding. Furthermore, the learned codes exhibit effective motion abstraction: applying them to novel scenes produces physically consistent transformations regardless of visual context. Our real-world experiments also confirm this robustness capability, achieving robust manipulation with minimal demonstrations in cluttered environments where geometric reasoning determines success. Thus, we demonstrate that effective motion latents for robot control can better emerge from understanding motion through its three-dimensional effects rather than pixel-level patterns.

Optimization · Discrete and Combinatorial Optimization

Changliang Zhou, Canhong Yu, Shunyu Yao, Xi Lin, Zhenkun Wang, Yu Zhou, Qingfu Zhang

Multi-task neural routing solvers have emerged as a promising paradigm for their ability to solve multiple vehicle routing problems (VRPs) using a single model. However, existing neural solvers typically rely on predefined problem constraints or require per-problem fine-tuning, which substantially limits their zero-shot generalization ability to unseen VRP variants. To address this critical bottleneck, we propose URS, a unified neural routing solver that achieves zero-shot generalization across a wide range of unseen VRPs with a single model. We propose a unified data representation (UDR) that replaces problem enumeration with data unification, thereby broadening the problem coverage and reducing reliance on domain expertise. In addition, we introduce a Mixed Bias Module (MBM) during encoding to improve node embeddings, which efficiently captures multiple priors inherent to various problems. On top of the UDR, we develop a problem-conditioned parameter generator to further improve zero-shot generalization. Extensive experiments show that URS consistently produces high-quality solutions for 110 VRP variants (including 99 unseen variants) while demonstrating impressive scalability to large-scale instances with up to 7000 nodes. To the best of our knowledge, URS is the first neural solver to handle over 100 VRP variants with a single model.

Applications · Chemistry, Physics, and Earth Sciences

Hongyu Wang, Weijian Liu, Mingzhen Li, Hongtao Xu, Yan Wang, Weile Jia, Guangming Tan

Discovering atom-level phenomena requires molecular dynamics (MD) simulations with ab initio accuracy. Machine learning interatomic potentials (MLIPs) enable stable, high-accuracy MD simulations, and their models exhibit scaling-law trends similar to large language models. However, the lack of scalable and efficient distributed training systems for conservative MLIPs makes them difficult to scale. This is because conservative MLIPs inherently follow a double-backward execution pattern, which involves computing gradients during the forward pass. This pattern creates a mismatch with existing distributed training systems, especially for pipeline parallelism. Therefore, we present JanusPipe, an efficient 3D-parallel (PP/DP/GP) training system tailored for conservative MLIPs. It integrates SymFold to enable memory-efficient pipeline parallelism for conservative MLIPs, and WaveK to reduce pipeline bubbles by balancing the four-phase compute time. Experimental results on 32 GPUs show that JanusPipe improves throughput by $1.51\times$ and $1.45\times$ on average over 1F1B and Hanayo, respectively.

Social Aspects · Alignment

Etienne Casanova, Rafal Kocielnik, R. Michael Alvarez

Pre-trained Large Language Models (LLMs) are increasingly used for zero-shot annotation and LLM-as-a-judge tasks, yet their reliability hinges on how pre-trained priors interact with user-provided instructions. We investigate three dimensions of this interaction: (1) how an LLM’s familiarity with data and task definitions affects performance, (2) the extent to which additional information in prompts can correct zero-shot errors (“decision stickiness”), and (3) model susceptibility to misaligned task definitions. Through experiments on toxicity detection across diverse datasets (spanning social media, gaming, news, and forums) using both dense and mixture-of-experts models, we find that nearly two-thirds of zero-shot errors are resistant to correction, with an overall rescue rate (fraction of initial errors corrected by prompting) of only 36.4%. High-confidence errors prove especially resistant to correction. When given misaligned definitions, LLMs follow them while maintaining confidence levels unchanged from the aligned condition. Crucially, we introduce Definition-Specific Familiarity (DSF), a metric measuring alignment between a model’s internal concept and the task definition. After controlling for dataset-level confounds, DSF shows positive association with model performance (partial r = +0.34), while text memorization as measured by ROUGE-L shows no positive association (partial r = −0.19). Overall, these findings suggest clear limits on prompt-based correction in annotation tasks and underscore the importance of definition alignment over text-level memorization.

Deep Learning · Generative Models and Autoencoders

Yangtian Zhang, Zhe Wang, Arthur Gretton, ZHITAO YING, David van Dijk, Michalis Titsias, Jiaxin Shi

Non-monotonic sequence generation methods, such as masked diffusion models, provide a flexible alternative to left-to-right autoregressive modeling by allowing tokens to be generated in non-fixed and prescribed orders. Despite their practical advantages, most existing non-monotonic models are order-agnostic and rely on a fixed-length masked token grid, limiting their ability to support variable-length generation and adaptive insertion order. In this work, we introduce a probabilistic framework for learning insertion order in variable-length insertion models. We formalize a bijective correspondence between insertion trajectories and permutations, which enables an exact reparameterization of the data likelihood as a sum over permutations. Building on this result, we propose the **Insertion Process (IP)**, a stochastic generative model that jointly learns *where* to insert, *what* to insert, and *when* to terminate, trained via permutation-based variational inference. Unlike prior masked or fixed-canvas approaches, IP natively supports variable-length generation and learns data-driven preferences over insertion orders. Experiments on planning benchmarks and molecular SMILES generation demonstrate that learning insertion order improves both modeling quality and generalization in domains without a canonical left-to-right structure.

Theory · Probabilistic Methods

Laura Lützow, Michael Eichelbeck, Mykel Kochenderfer, Matthias Althoff

Conformal prediction is a popular uncertainty quantification method that augments a base predictor to return sets of predictions with statistically valid coverage guarantees. However, current methods are often computationally expensive and data-intensive, as they require constructing an uncertainty model before calibration. Moreover, existing approaches typically represent the prediction sets with intervals, which limits their ability to capture dependencies in multi-dimensional outputs. We address these limitations by introducing zono-conformal prediction, a novel approach inspired by interval predictor models and reachset-conformant identification that constructs prediction zonotopes with assured coverage. By placing zonotopic uncertainty sets directly into the model of the base predictor, zono-conformal predictors can be identified via a single, data-efficient linear program. While we can apply zono-conformal prediction to arbitrary nonlinear base predictors, we focus on feed-forward neural networks in this work. Aside from regression tasks, we also construct optimal zono-conformal predictors in classification settings where the output of an uncertain predictor is a set of possible classes. We provide probabilistic coverage guarantees and present methods for detecting outliers in the identification data. In extensive numerical experiments, we show that zono-conformal predictors are less conservative than interval predictor models and standard conformal prediction methods, while achieving a similar coverage over the test data.

Applications · Chemistry, Physics, and Earth Sciences

Teddy Koker, Abhijeet Gangan, Mit Kotak, Jaime Marian, Tess Smidt

Many materials properties depend on higher-order derivatives of the potential energy surface, yet machine learned interatomic potentials (MLIPs) trained with a standard loss on energy, force, and stress errors can exhibit error in curvature, degrading the prediction of vibrational properties. We introduce phonon fine-tuning (PFT), which directly supervises second-order force constants of materials by matching MLIP energy Hessians to DFT-computed force constants from finite displacement phonon calculations. To scale to large supercells, PFT stochastically samples Hessian columns and computes the loss with a single Hessian-vector product. We also use a simple co-training scheme to incorporate upstream data to mitigate catastrophic forgetting. On the MDR Phonon benchmark, PFT improves Nequix MP by 55% on average across phonon thermodynamic properties and achieves state-of-the-art accuracy among models trained on Materials Project trajectories. PFT also generalizes to improve properties beyond second-derivatives, improving thermal conductivity predictions that rely on third-order derivatives of the potential energy.

Probabilistic Methods · Monte Carlo and Sampling Methods

Mehmet Berk Sahin, Behzad Sharif, Abolfazl Hashemi

Sampling from high-dimensional, non-log-concave distributions with unnormalized densities constitutes a fundamental challenge in machine learning, particularly when gradient information is inaccessible or computationally prohibitive. While Langevin dynamics provides a robust mechanism for gradient-based sampling, its extension to the derivative-free setting is frequently compromised by high variance and a lack of rigorous convergence guarantees in non-convex landscapes. In this work, we propose a principled variance-reduced zeroth-order Langevin dynamics framework that addresses these limitations for both general non-log-concave black-box sampling and inverse problems utilizing pre-trained score-based generative priors. We introduce a novel gradient estimator that significantly mitigates the variance inherent in traditional zeroth-order methods, enabling stable navigation of complex, multimodal posterior distributions. Theoretically, we establish the first non-asymptotic complexity bounds for this class of algorithms, proving convergence to the target distribution in terms of $\varepsilon$-relative Fisher information, and, under a Poincare inequality, squared total variation distance, specifically for non-log-concave densities. We empirically validate our framework, demonstrating superior mixing and sampling accuracy on standard black-box benchmarks and establishing state-of-the-art performance for derivative-free linear and nonlinear inverse problems.

Social Aspects · Safety

Emanuele Ricco, Elia Onofri, Lorenzo Cima, Stefano Cresci, Roberto Di Pietro

Hallucinations---fluent but factually incorrect responses---pose a major challenge to the reliability of language models, especially in multi-step or agentic settings. This work investigates hallucinations in small-sized LLMs through a geometric perspective, starting from the hypothesis that when models generate multiple responses to the same prompt, genuine ones exhibit tighter clustering in the embedding space, we prove this hypothesis and, leveraging this geometrical insight, we also show that it is possible to achieve a consistent level of separability. This latter result is used to introduce a label-efficient propagation method that classifies large collections of responses from just 30–50 annotations, achieving F1 scores above 90\%. Our findings, framing hallucinations from a geometric perspective in the embedding space, complement traditional knowledge-centric and single-response evaluation paradigms, paving the way for further research.

Alex Hernandez-Garcia, Alexandra Volokhova, Ezekiel Williams, Dounia Shaaban Kabakibo, Mélisande Teng

The accelerated development, deployment and adoption of artificial intelligence systems has been fuelled by the increasing presence of big tech in the AI field. This trend has been accompanied by growing ethical concerns and intensified societal and environmental impacts. This position paper argues that irresponsible AI development is strongly driven by big tech's influence and involvement in the field. We develop this argument by laying out the factors through which this influence leads to irresponsible AI. First, we examine the growing and disproportionate influence of big tech in AI research and argue that its drive for scaling and general-purpose systems is fundamentally at odds with the responsible, ethical, and sustainable development of AI. Second, we review key current environmental and societal negative impacts of AI and trace their connections to big tech's influence. Third, we discuss the underlying economic forces driving big tech's actions. Finally, as a call to action, we highlight the need for AI researchers to counter big tech's influence, and review and propose strategies that build on the responsibility of implicated actors and collective action.

Social Aspects · Everything Else

Alex Hernandez-Garcia, Alexandra Volokhova, Ezekiel Williams, Dounia Shaaban Kabakibo, Mélisande Teng

The accelerated development, deployment and adoption of artificial intelligence systems has been fuelled by the increasing presence of big tech in the AI field. This trend has been accompanied by growing ethical concerns and intensified societal and environmental impacts. This position paper argues that irresponsible AI development is strongly driven by big tech's influence and involvement in the field. We develop this argument by laying out the factors through which this influence leads to irresponsible AI. First, we examine the growing and disproportionate influence of big tech in AI research and argue that its drive for scaling and general-purpose systems is fundamentally at odds with the responsible, ethical, and sustainable development of AI. Second, we review key current environmental and societal negative impacts of AI and trace their connections to big tech's influence. Third, we discuss the underlying economic forces driving big tech's actions. Finally, as a call to action, we highlight the need for AI researchers to counter big tech's influence, and review and propose strategies that build on the responsibility of implicated actors and collective action.

Applications · Neuroscience, Cognitive Science

Ezekiel Williams, Alexandre Payeur, Guillaume Lajoie

Biological and neuromorphic recurrent neural networks (RNNs) are subject to spatial and temporal locality constraints on the information that can plausibly be used during learning. A common strategy to satisfy these constraints is to modify gradient descent by neglecting non-local terms to varying degrees, as in random feedback local online (RFLO) learning and truncated backpropagation through time (tBPTT). However, the learning dynamics of these algorithms, and how they compare with BPTT, remain poorly understood. Here, we apply dynamical systems theory to data-aligned linear RNNs to compare stationary solutions, stability properties, and convergence rates, finding a close relationship between BPTT and one-step tBPTT—in contrast with qualitatively distinct behavior for RFLO. We further observe that the solutions learned by RFLO are restricted to low-rank perturbations of initial parameters, a result which holds beyond the data-aligned setting. Our work provides fundamental insights into how locality constraints shape RNN learning dynamics, with implications for neuroscientific models of learning and alternative optimization approaches for state-space models.

Applications · Chemistry, Physics, and Earth Sciences

Yadi Cao, Sicheng Lai, Jiahe Huang, Yang Zhang, Zach Lawrence, Rohan Bhakta, Izzy Thomas, Mingyun Cao, Chung-Hao Tsai, Zihao Zhou 等

Evaluating LLM agents for scientific tasks has focused on token costs while ignoring tool-use costs like simulation time and experimental resources. As a result, metrics like pass@k become impractical under realistic budget constraints. To address this gap, we introduce SimulCost, the first benchmark targeting cost-sensitive parameter tuning in scientific simulations. SimulCost compares LLM tuning cost-sensitive parameters against traditional scanning approach in both accuracy and computational cost, spanning 2,916 single-round (initial guess) and 1,900 multi-round (adjustment by trial-and-error) tasks across 12 simulators from fluid dynamics, solid mechanics, and plasma physics. Each simulator's cost is analytically defined and platform-independent. Frontier LLMs achieve 46--64\% success rates in single-round mode, dropping to 35--54\% under high accuracy requirements, rendering their initial guesses unreliable especially for high accuracy tasks. Multi-round mode improves rates to 71--80\%, but LLMs are 1.5--2.5$\times$ slower than traditional scanning, making them uneconomical choices. We also investigate parameter group correlations for knowledge transfer potential, and the impact of in-context examples and reasoning effort, providing practical implications for deployment and fine-tuning. We open-source SimulCost as a static benchmark and extensible toolkit to facilitate research on improving cost-aware agentic designs for scientific simulations, and for expanding new simulation environments.

Social Aspects · Safety

Zezhong WANG, Xueyang Tang, RUI LIAN, Yang Lou, Heqing Huang

As Large Language Model (LLM) agents are increasingly deployed in complex environments, multi-turn interaction attacks have become a significant security challenge. Existing detection methods typically rely on historical context. However, this retrospective logic struggles to identify deep malicious intents that are split across turns to hide future risks. Inspired by speculative decoding, we propose the Speculative Safety Honeypot (SSH) framework. SSH uses a multi-agent simulation system composed of small LLMs to build an action-level speculate-and-verify workflow. In the speculation stage, SSH predicts future behaviors of the target agent and asynchronously builds a trajectory tree to expose potential risks in advance. In the verification stage, the system uses the target agent's real actions to calibrate and prune the trajectory tree, effectively reducing false positives. As a plug-and-playable component, SSH provides existing detectors with rich decision redundancy beyond the current interaction slice. By judging risk based on the evolution of the entire trajectory tree rather than a single point in time, the system reduces the reliance on the absolute precision of individual detection components. This improves the defense resilience and the warning lead-time of agent systems against complex temporal attacks.

Theory · Learning Theory

Arshia Soltani Moakhar, Faraz Ghahremani, Kiarash Banihashem, MohammadTaghi Hajiaghayi

Decision tree learning has long been a central topic in theoretical computer science, driven by its practical importance. A fundamental and widely used method for decision tree construction is the top-down greedy heuristic, which recursively splits on the most influential variable. Despite its empirical success, theoretical analysis of this heuristic has been limited. A recent breakthrough by Blanc et al. (ITCS, 2020) provided the first rigorous theoretical guarantees for the greedy approach, but only under the uniform distribution. We extend this analysis to the more general and practically relevant setting of arbitrary product distributions. Our main result shows that for any function $f$ computable by an optimal decision tree of size $s$, maximum depth $D_{\text{opt}}$, and average depth $\Delta_{\text{opt}}$, the greedy heuristic constructs an $\epsilon$-approximating tree whose size grows at most with $\exp\bigl(\Delta_{\text{opt}} D_{\text{opt}} \log(e/\epsilon)\bigr)$. In the special case where the optimal tree is a full binary tree, this bound improves upon the bound of Blanc et al. and holds under a strictly broader class of distributions. Moreover, we present an algorithm based on the top-down greedy heuristic that is entirely **parameter-free**—it requires no prior knowledge of the optimal tree's size or depth—offering a practical advantage over Blanc et al.'s method.

Deep Learning · Everything Else

Zhaohong Huang, Yuxin Zhang, Wenjing Liu, Fei Chao, Rongrong Ji

Test-time adaptation (TTA) has emerged as a promising paradigm for vision–language models (VLMs) to bridge the distribution gap between pre-training and test data. Recent works have focused on backpropagation-free TTA methods that rely on cache-based designs, but these introduce two key limitations. First, inference latency increases as the cache grows with the number of classes, leading to inefficiencies in large-scale settings. Second, suboptimal performance occurs when the cache contains insufficient or incorrect samples. In this paper, we present Prototype-Based Test-Time Adaptation (PTA), an efficient and effective TTA paradigm that uses a set of class-specific knowledge prototypes to accumulate knowledge from test samples. Particularly, knowledge prototypes are adaptively weighted based on the zero-shot class confidence of each test sample, incorporating the sample's visual features into the corresponding class-specific prototype. It is worth highlighting that the knowledge from past test samples is integrated and utilized solely in the prototypes, eliminating the overhead of cache population and retrieval that hinders the efficiency of existing TTA methods. This endows PTA with extremely high efficiency while achieving state-of-the-art performance on 15 image recognition benchmarks and 4 robust point cloud analysis benchmarks. For example, PTA improves CLIP’s accuracy from 65.64\% to 69.38\% on 10 cross-domain benchmarks, while retaining 92\% of CLIP’s inference speed on large-scale ImageNet-1K. In contrast, the cache-based TDA achieves a lower accuracy of 67.97\% and operates at only 50\% of CLIP’s inference speed.

Haozhe WANG, Qixin Xu, Changpeng Wang, Taofeng Xue, Chong Peng, Wenhu Chen, Fangzhen Lin

Achieving robust perception-reasoning synergy is a central goal for advanced Vision-Language Models (VLMs). Recent advancements have pursued this goal via architectural designs or agentic workflows. However, these approaches are often limited by static textual reasoning or complicated by the significant compute and engineering burden of external agentic complexity. Worse, this heavy investment does not yield proportional gains, often witnessing a "seesaw effect" on perception and reasoning. This motivates a fundamental rethinking of the true bottleneck. In this paper, we argue that the root cause of this trade-off is an ambiguity in modality credit assignment: when a VLM fails, is it due to flawed perception ("bad seeing") or flawed logic ("bad thinking")? To resolve this, we introduce a reinforcement learning framework that improves perception-reasoning synergy by reliably rewarding the perception fidelity. We explicitly decompose the generation process into interleaved perception and reasoning steps. This decoupling enables targeted supervision on perception. Crucially, we introduce Perception Verification (PV), leveraging a "blindfolded reasoning" proxy to reward perceptual fidelity independently of reasoning outcomes. Furthermore, to scale training across free-form VL tasks, we propose Structured Verbal Verification, which replaces high-variance LLM judging with structured algorithmic execution. These techniques are integrated into a Modality-Aware Credit Assignment (MoCA) mechanism, which routes rewards to the specific source of error -- either bad seeing or bad thinking -- enabling a single VLM to achieve simultaneous performance gains across a wide task spectrum.