AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

arXiv

Holistic Fusion: Task- and Setup-Agnostic Robot Localization and State Estimation with Factor Graphs

Julian Nubert, Turcan Tuna, Jonas Frey, Cesar Cadena, Katherine J. Kuchenbecker, Shehryar Khattak, Marco Hutter

Seamless operation of mobile robots in challenging environments requires low-latency local motion estimation and accurate global localization. While most sensor-fusion approaches are designed for specific scenarios, this work introduces a flexible open-source solution for task- and setup-agnostic multimodal sensor fusion distinguished by its generality and usability. Holistic Fusion formulates sensor fusion as a combined estimation problem of i) the local and global robot state and ii) a (theoretically unlimited) number of dynamic variables, including automatic alignment of reference frames; this formulation fits countless real-world applications without conceptual modifications, offering a comprehensive solution beyond hard-coded/task-specific approaches. The proposed factor-graph formulation enables direct fusion of an arbitrary number of absolute, local, and landmark measurements expressed with respect to different frames by explicitly including them as states in the optimization and modeling their evolution as random walks. Moreover, local smoothness and consistency receive particular attention to prevent estimation jumps. Holistic Fusion enables low-latency and smooth online state estimation on typical robot hardware while simultaneously providing low-drift global localization at the IMU measurement rate. The efficacy of this released framework [1] is demonstrated in five real-world scenarios on three robotic platforms with distinct task requirements, highlighting the advantages of fusing multiple absolute measurement types [2]. [1] Code: https://github.com/leggedrobotics/holistic_fusion [2] Project: https://leggedrobotics.github.io/holistic_fusion

arXiv

A Bit of Freedom Goes a Long Way: Classical and Quantum Algorithms for Reinforcement Learning under a Generative Model

Andris Ambainis, Joao F. Doriguello, Debbie Lim

We propose novel classical and quantum online algorithms for learning finite- and infinite-horizon Markov Decision Processes (MDPs). Our algorithms are based on a hybrid online-offline reinforcement learning model wherein the agent can, from time to time, freely interact with the environment in a generative sampling fashion, i.e., by having access to a "simulator". By employing known classical and new quantum algorithms for approximating optimal policies under a generative model within our learning algorithms, we show that it is possible to avoid several paradigms from RL like "optimism in the face of uncertainty" and "posterior sampling" and instead compute and use optimal policies directly, which yields better regret bounds compared to previous works. Our quantum algorithms obtain regret bounds which only a $\operatorname{poly}\log{T}$ dependence on the number of time steps $T$, thus breaking the $O(\sqrt{T})$ classical barrier. Our infinite-horizon discounted regret bound is brand new, while in the finite- and infinite-horizon undiscounted settings, our results match the time dependence of some prior quantum works, but with improved dependence on other parameters like state space size $S$ and action space size $A$.

arXiv

Bifocal Attention: Harmonizing Geometric and Spectral Positional Embeddings for Algorithmic Generalization

Kanishk Awadhiya

Rotary Positional Embeddings (RoPE) have become the standard for Large Language Models (LLMs) due to their ability to encode relative positions through geometric rotation. However, we identify a significant limitation we term ''Spectral Rigidity'': standard RoPE utilizes a fixed geometric decay ($θ^{-i}$) optimized for local syntactic coherence, which fails to capture the long-range, periodic structures inherent in recursive logic and algorithmic reasoning. This results in a ''Structure Gap'', where models trained on shallow reasoning chains fail to extrapolate to deeper recursive steps. In this work, we introduce Bifocal Attention, an architectural paradigm that decouples positional encoding into two distinct modalities: Geometric Eyes (Standard RoPE) for precise token-level manipulation, and Spectral Eyes (Learnable Harmonic Operators) for tracking long-range recursive depth. We propose a novel training protocol, Spectral Evolution, which initializes positional frequencies as static geometric parameters but allows them to evolve via gradient descent into a harmonic basis optimized for the specific algorithmic topology of the task.

arXiv

A Scaffolded GenAI Lab in Early Undergraduate CS: A Mixed-Methods, Multi-Course Evaluation

Ethan Dickey, Andres Bejarano, Rhianna Kuperus, Bárbara Fagundes

Background and Context. Generative AI (GenAI) tools are increasingly used in programming courses, but we have limited evidence about how brief instruction can foster responsible, learning-oriented use. Objectives. We evaluate "AI-Lab", a scaffolded GenAI literacy intervention, asking how students' self-reported GenAI usage and their openness and comfort using GenAI for conceptual, debugging, and homework tasks change after participation. Methods. Across two semesters in three CS courses and one first-year engineering course at a U.S. university, we deployed the "AI-Lab" (pre-lab orientation, in-class critique of GenAI outputs, and a required homework reflection), collecting paired pre/post surveys (Perception N=831; Usage N=826) and six post-intervention focus groups; primary inferential analyses used the three CS courses (N=778 and 773, respectively). We analyzed survey shifts with paired non-parametric tests and focus groups via thematic analysis. Findings. Openness increased for conceptual questions and homework help, and comfort increased for conceptual, debugging, and homework scenarios; self-reported frequency of GenAI use for homework and projects remained stable, while self-reported use for debugging increased. Focus group participants described adopting more iterative prompting strategies, becoming more skeptical of correctness, and articulating clearer boundaries around integrity and dependence. Implications. A short, structured intervention can shift students' reported comfort with and willingness to use GenAI and influence the strategies they describe for engaging with it without increasing overall self-reported use on graded work. These results motivate future work triangulating surveys with behavioral traces and learning measures.

arXiv

Perception-Aligned AI Outputs: End-to-End Visual Prediction for Uncertainty Communication in Clinical Decision-Making

Mohammad Eslami, Solale Tabarestani, Saber Kazeminasab, Ehsan Adeli, Glyn Elwyn, Tobias Elze, Mengyu Wang, Nazlee Zebardast, Lucia Sobrin, Nassir Navab, Daniel Shu Wei Ting, Malek Adjouadi

Explainable Artificial Intelligence (XAI) is essential for trustworthy AI in healthcare, yet many existing methods rely on technical explanations that are difficult for clinicians and patients to interpret. We introduce Visualized Learning for Machine Learning (VL4ML), a human-centered explainability framework that communicates model predictions and uncertainty through intuitive visual representations rather than numerical or post-hoc explanations. By encoding diagnostic information in colors, patterns, and spatial structures, VL4ML enables users to interpret predictions without requiring knowledge of model internals or statistical expertise. We demonstrate the framework across multiple clinical tasks, including classification, regression, longitudinal prediction, and multimodal analysis. Its effectiveness was evaluated through a human-centered study involving 158 participants (39.2% clinical professionals) and an expert interpretability assessment. More than 79% of participants positively rated the visual explanations across evaluation dimensions, 84.0% found them more memorable than numeric outputs, and 76.9% reported faster decision-making. Over 82% successfully perceived uncertainty embedded in the visual representations without prior statistical training. No significant differences were observed between clinicians and non-clinicians or between male and female participants, indicating broad accessibility. These results suggest that VL4ML complements existing XAI and uncertainty quantification methods by providing intuitive, universally interpretable visual explanations that support transparent and trustworthy clinical decision-making.

ICML 2026

Any3D-VLA: Enhancing VLA Robustness via Diverse Point Clouds

Xianzhe Fan, Shengliang Deng, Xiaoyang Wu, Yuxiang Lu, Zhuoling Li, Mi Yan, Yujia Zhang, Zhizheng Zhang, He Wang, Hengshuang Zhao

Existing Vision-Language-Action (VLA) models typically take 2D images as visual input, which limits their spatial understanding in complex scenes. How can we incorporate 3D information to enhance VLA capabilities? We conduct a pilot study across different observation spaces and visual representations. The results show that explicitly lifting visual input into point clouds yields representations that better complement their corresponding 2D representations. To address the challenges of (1) scarce 3D data and (2) the domain gap induced by cross-environment differences and depth-scale biases, we propose Any3D-VLA. It unifies the simulator, sensor, and model-estimated point clouds within a training pipeline, constructs diverse inputs, and learns domain-agnostic 3D representations that are fused with the corresponding 2D representations. Simulation and real-world experiments demonstrate Any3D-VLA's advantages in improving performance and mitigating the domain gap. Our project homepage is available at https://xianzhefan.github.io/Any3D-VLA.github.io.

ICML 2026

Addressing Instrument-Outcome Confounding in Mendelian Randomization through Representation Learning

Shimeng Huang, Matthew R Robinson, Francesco Locatello

Mendelian Randomization (MR) is a prominent observational epidemiological research method, designed to address unobserved confounding when estimating causal effects. It is closely related to instrumental variable (IV) methods, where genetic variants serve as instruments to infer causal relationships from observational data. However, the core assumptions required for valid IV analysis---particularly the independence between instruments and unobserved confounders---are untestable and often violated in practice. In MR, such violations commonly arise when genetic variants are correlated with environmental factors (e.g., population stratification and assortive mating), leading to confounding between instruments and outcomes. At the same time, MR studies increasingly include data collected across multiple environments or populations, providing an opportunity to address these violations. Leveraging this setting, we propose a representation learning framework that exploits multi-environment data to recover latent exogenous components of genetic instruments suitable for causal inference. We provide theoretical insights into when and how the learned components can act as valid instruments, and we demonstrate the effectiveness of our approach through simulations and semi-synthetic experiments using genetic data from the All of Us Biobank.

ICML 2026

AVI-Bench: Toward Human-like Audio-Visual Intelligence of Omni-MLLMs

Yaoting Wang, Ziyi Zhang, Wenming Tu, Shaoxuan Xu, Wenjie Du, Cheng Liang, Weijun Wang, Yuanchao Li, Guangyao Li, Hao Fei, Yuanchun Li, Henghui Ding, Yunxin Liu

Recent advances in Omni-Multimodal Large Language Models (Omni-MLLMs) have enabled strong integration of vision, audio, and language. However, their audio-visual intelligence (AVI) remains insufficiently evaluated due to the lack of systematic and comprehensive benchmarks. We introduce **AVI-Bench**, a cognitively inspired benchmark that evaluates Omni-MLLMs across three stages, perception, understanding, and reasoning, through cross-modal tasks requiring joint audio-visual interpretation. This design enables fine-grained diagnosis of model capabilities and failure modes. To further assess robustness beyond familiar domains, we propose **AVI-Bench-PriSe**, an extension that probes models' primitive audio-visual sensation using unfamiliar, low-semantic stimuli, testing generalization beyond common training distributions. Extensive experiments on both open-source and closed-source models reveal substantial limitations in current Omni-MLLMs. Based on these findings, we present a **four-level AVI taxonomy**. Overall, AVI-Bench provides a principled evaluation framework to guide the development of more robust and generalizable AVI. Project website: https://fudancvl.github.io/AVI-Bench

ICML 2026

OptMaster: A DAG-Based Framework for Formulation and Heuristic Discovery in Optimization

Hang Lin, Yuanpeng Gao, Yuzhi Zhang, Kun Yuan, Gang Yan, Siheng Chen, Linfeng Zhang, Weinan E

Optimization problems are fundamental across science and industry, including planning, scheduling, and resource allocation. While LLMs show promise in automating optimization, they struggle to bridge the gap between real-world requirements and both mathematical formulations and effective heuristic designs. Furthermore, the field lacks a unified framework that spans problem formulation and heuristic discovery for NP-hard settings. To address these challenges, we propose OptMaster, a unified framework that spans optimization from formulation to heuristic discovery, structuring the process as a Directed Acyclic Graph (DAG) where each node represents a candidate solution. The DAG architecture enables cross-branch knowledge transfer when search progress stagnates. Within each node, we further replace textual self-reflection with independently generated verification code, grounding the evaluation in deterministic computation to suppress hallucinations. OptMaster achieves competitive performance across two optimization paradigms. In Formulation Intelligence, OptMaster achieves state-of-the-art accuracy across the three most challenging benchmarks in the field. In Heuristic Discovery, OptMaster surpasses the best known solutions on Circle Packing ($n=26, 32$) and achieves a cut of 9,590 on Gset70 with significantly reduced time and search budgets.

ICML 2026

From Extrinsic to Intrinsic: Geodesic-Guided Representation Learning for 3D Geometric Data

Yuming Zhao, Junhui Hou, Qijian Zhang, Jia Qin, Ying He

Geometric analysis fundamentally distinguishes between extrinsic and intrinsic perspectives. The dominant paradigm in current 3D representation learning relies on either extrinsic spatial structures or high-level semantics, struggling to capture the essence of shape identity and underlying manifold topology. To bridge this gap, we introduce a novel 3D representation learning paradigm, namely PRISM, for Pre-training, which learns isometric embeddings by Recovering the Intrinsic Surface geodesic Metric. PRISM incorporates a topology-enforcing objective that explicitly constrains the structure of latent space, alongside a specialized two-stage training recipe mitigating sample imbalance inherent in the distribution of geodesic distances. Experiments demonstrate that our approach shows satisfactory accuracy, robustness, and high efficiency in geodesic distance prediction and achieves superior performance across diverse downstream tasks, including shape recognition, surface parameterization, and non-rigid correspondence. Our code will be made publicly available.

ICML 2026

Reliable Confidence Alignment for Generalized Category Discovery

Jiawei Yu, Zijian Gao, Tianjiao Wan, Xuan Liu, Cheng Yang, Kele Xu

Generalized Category Discovery (GCD) requires models to categorize an unlabeled pool containing known and novel classes under sparse supervision. We identify a systemic confidence bias inherent in existing parametric methods: while entropy regularization prevents class collapse, it indiscriminately suppresses predictive certainty on all unlabeled instances. This bias drives a distributional wedge between labeled and unlabeled samples of the same category, forcing models to sacrifice their stability on known classes to achieve plasticity for new ones. To resolve this, we propose Reliable Confidence Alignment (RCA), a plug-and-play framework grounded in Evidential Deep Learning. RCA first establishes high certainty anchors on labeled data using a Reliable Anchor for Certainty (RAC) module. Then, we introduce Cross-view Confidence Alignment (CCA) to propagate this grounded reliability to the unlabeled discovery set. Thus, RCA captures the fine-grained geometry of the probability simplex, effectively calibrating the model's epistemic uncertainty. Extensive evaluations on coarse- and fine-grained benchmarks demonstrate that RCA effectively rectifies the confidence landscape, significantly mitigating performance decay on known classes without compromising novel-class discovery.

ICML 2026

Grouter: Decoupling Routing from Representation for Accelerated MoE Training

Yuqi Xu, Rizhen Hu, Zihan Liu, Mou Sun, Kun Yuan

Traditional Mixture-of-Experts (MoE) training typically proceeds without any structural priors, effectively requiring the model to simultaneously train expert weights while searching for an optimal routing policy within a vast combinatorial space. This entanglement often leads to sluggish convergence and training instabilities. This paper introduces Grouter a preemptive routing method that by distilling high-quality structures from fully-trained MoE models and serving as a fixed router for target models. By decoupling structural optimization from weight updates, Grouter significantly accelerates both the speed and quality of model convergence. To ensure the framework's versatility, we also introduce expert folding to adapt Grouter across varying model configurations and expert tuning to rebalance workloads across different data distributions. Furthermore, by leveraging the structural priors provided by preemptive routing, we can implement targeted optimizations to further enhance training throughput. Experiments demonstrate that Grouter achieves superior performance and efficiency which boosts pre-training data utilization by $\textbf{4.28$\times$}$ and achieves up to $\textbf{33.5$\%$}$ throughput acceleration, establishing preemptive routing as a fundamental paradigm for scalable MoE training. We publicly release our code and pretrained Grouter checkpoints.

ICML 2026

ScoreMix: Synthetic Data Generation by Score Composition in Diffusion Models Improves Recognition

Parsa Rahimi, Sébastien Marcel

Synthetic data generation is increasingly used in machine learning for **training and data augmentation**. Yet, many current strategies rely on external foundation models or datasets, which can be restricted by policy or legal constraints, especially for sensitive modalities such as human face images and videos. We propose **ScoreMix**, a **self-contained data augmentation** method to boost recognition performance by leveraging score compositionality in class-conditioned diffusion models. ScoreMix mixes class-conditioned scores along reverse diffusion trajectories, yielding domain-specific hard augmentations without external resources. We systematically study class-selection strategies and find that mixing classes that are distant in the discriminator embedding space yields larger gains, providing **up to 3\% additional average improvement across benchmarks** over proximity-based selection. Interestingly, we observe that learned condition and embedding spaces are largely uncorrelated under standard alignment metrics, and that condition-space distances are weakly correlated to downstream gains. Across **8 public face recognition benchmarks**, ScoreMix improves accuracy by **up to 7 percentage points** without hyperparameter search, highlighting robustness and practicality. Project page: https://parsa-ra.github.io/scoremix/ .

ICML 2026

Attention's forward pass and Frank-Wolfe

Albert Alcalde, Borjan Geshkovski, Domènec Ruiz-Balet

We analyze the hardmax limit of self-attention dynamics for token embeddings in the zero-temperature regime $(\beta \to +\infty)$ and relate it to finite-$\beta$ behavior. In this limit, the update rule can be viewed as a Frank-Wolfe step for a quadratic objective over the convex hull of the current tokens. When the key-query matrix is negative semidefinite, the dynamics converge with the standard sublinear rate $\mathcal{O}(t^{-1})$ on the quadratic energy, whereas in the positive semidefinite case, extending the hardmax rule to the convex hull induces a Voronoi structure: vertices are stationary, interior points remain in their initial cells, and each token moves along a straight line toward its cell's vertex with exponential convergence under a step-size bounded away from zero. We additionally establish well-posedness of the associated ODE limit in this regime. For finite $\beta$, we model self-attention as a Markov chain and prove *dynamic metastability*: interior tokens reach near-vertex configurations in a constant number of steps and remain trapped for times exponential in $\beta$ with high probability, before eventual collapse to some point within the initial convex hull. Thus, hardmax dynamics accurately approximate the finite-$\beta$ process over exponentially long time horizons.

ICML 2026

Why Specialist Models Still Matter: A Heterogeneous Multi-Agent Paradigm for Medical Artificial Intelligence

Yanan Wang, Shuaicong Hu, Jian Liu, Guohui Zhou, Aiguo Wang, Cuiwei Yang

The impressive performance of generalist large language models (LLMs) such as GPT and Claude in healthcare raises a critical question: will domain-specific medical specialist models become obsolete? We argue that the future of medical artificial intelligence (AI) lies not in building monolithic medical foundation models, nor in replacing human expertise, but in orchestrating collaboration among generalist LLMs, domain-specific specialist models, and clinicians. We propose HetMedAgent, a heterogeneous medical multi-agent framework that enables conflict-aware evidence fusion, uncertainty-based clinician intervention triggering, and adaptive threshold calibration. Experiments on three real-world clinical decision-making tasks demonstrate that the synergy between generalist LLMs and domain-specific specialist models significantly outperforms using either type of model alone, validating the irreplaceable value of specialist models in modality-specific analysis. HetMedAgent represents a shift from building medical LLMs or foundation models to multi-agent collaboration, achieving a balance between general reasoning capabilities and domain-specific precision.

ICML 2026

MSP: Probabilistically Consistent Multi-Scale Action Generation

Zhixuan Lin, Gengqi Liu, Chao Zheng, Gao Lin, Jindong Yu, Song Gao, Fei Wang

In robotic imitation learning, accurately modeling the multimodality and temporal correlations of long-horizon action sequences remains challenging. Long-horizon tasks require preserving global task intent while executing precise low-level control; otherwise, local errors can accumulate and lead to failure. While recent coarse-to-fine autoregressive models have improved action generation, they struggle to maintain consistency across hierarchies, leading to suboptimal performance in long-horizon tasks. To address these shortcomings, we propose Probabilistically Consistent Multi-Scale Action Generation (MSP), a novel coarse-to-fine approach that promotes cross-scale consistency. MSP adopts a streamlined multi-scale design by directly downsampling in a continuous latent space. A scale-wise autoregressive Transformer is used to generate semantic conditions at each scale, which guide a lightweight MeanFlow model to capture multi-scale latent distributions, enabling probabilistically consistent refinement across scales. Through extensive simulation and real-world experiments, including long-horizon, multi-task, and few-shot generalization settings, we show that MSP outperforms existing coarse-to-fine methods, achieving state-of-the-art performance with high efficiency.

ICML 2026

ROAMM: A Benchmark Dataset for Multimodal Human Attention Decoding and EEG-to-Text Modeling During Naturalistic Reading

Haorui Sun, Ardyn Vivienne Olszko, Niharika Singh, David C. Jangraw

We present Reading Observed At Mindless Moments (ROAMM), a multimodal dataset comprising 50 hours of simultaneous EEG and eye-tracking recordings collected during naturalistic multi-page reading from 44 participants. ROAMM includes synchronized physiological recordings, eye-movement events, page-level comprehension scores, and span-level mind-wandering (MW) annotations obtained using a retrospective self-report paradigm. We introduce a standardized leave-one-subject-out benchmark for MW detection and achieve up to 0.609 AUROC using supervised models. We additionally evaluate EEG-to-text decoding on reading segments with and without MW labels, showing that decoding performance decreases during MW episodes. ROAMM enables research on MW detection, EEG-to-text decoding, multimodal representation learning, and attention-related degradation of language representations during naturalistic reading.

ICML 2026

DynaSchedBench: Calibrated Dynamic Scheduling Benchmarks and Observability Paradox in LLM-based Scheduling Agents

Shijie Cao, Yuan Yuan, Jing Liu

Progress in neural combinatorial optimization for Dynamic Flexible Job Shop Scheduling Problem (DFJSP) is currently hindered by a methodological tension: static benchmarks encourage benchmark overfitting, while uncalibrated generators obscure algorithmic capability with stochastic noise. To resolve this, we introduce \textbf{DynaSchedBench}, a diagnostic framework for DFJSP that rigorously controls the instance-generation process. Instead of relying on parameter sampling, our approach utilizes Sequential Event-Space Calibrator (SESC) that computes a novel Schedule Stress Index (SSI) to stratify instances by difficulty. We demonstrate that SESC is substantially more computationally efficient than evolutionary baselines while converging reliably to the target metrics. The framework integrates modular components for instance generation, snapshot-based simulation, agents, evaluation, and visualization, thereby enabling rigorous testing of reactive and lookahead-based policies. Leveraging this calibrated environment, we identify key limitations of LLM-based scheduling agents. Specifically, in step-wise online decision-making for dynamic scheduling, we identify an ``Observability Paradox'': providing agents with oracle access to full structural information can degrade policy performance, underperforming concise information. Furthermore, despite substantial token overhead, tool-augmented and refinement strategies fail to reliably improve performance, and most LLM agents fail to consistently surpass strong dispatching baselines—behaving more like robust heuristic approximators than superior optimizers.

ICML 2026

Motion-Residual Conflict-Aware Time Reversal for Generative Inbetweening

Zhenbang Zhang, Zihui Cui, Haythem El-Messiry, Renmin Han, zhiqiang xu

Image-to-video (I2V) diffusion models have recently made generative inbetweening a practical reality by synthesizing semantically plausible intermediate frames between two keyframes. Among them, inference-time sampling schemes that re-use large pre-trained I2V backbones without any additional training are especially attractive. Yet current methods frequently exhibit temporal inconsistency and artifacts such as ghosting or reverse motion. A key reason is that the two trajectories are driven by distinct motion priors, each inherited from its own conditioning frame, and are simply stitched together without explicitly reconciling these priors. We introduce Motion-Residual Conflict-Aware Time Reversal (MR‑CATR), an inference-time sampling framework that aligns conflicting motion priors instead of discarding one of them or collapsing to a single start-conditioned prior. MR‑CATR first derives a motion-residual–based direction from the forward path, combined with an end-conditioned residual to form a consensus motion axis. This design suppresses bidirectional motion conflicts while still allowing end-frame information to refine the trajectory and enforce endpoint consistency. MR‑CATR can be seamlessly integrated into existing time-reversal samplers without changing model parameters. Experiments on generative inbetweening benchmarks show that our method produces videos with smoother motion, fewer artifacts, and consistently better quantitative scores and user preferences than prior strategies.

ICML 2026

ForesightKV: Optimizing KV Cache Eviction for Reasoning Models by Learning Long-Term Contribution

zican Dong, Peiyu Liu, Junyi Li, Zhipeng Chen, Han Peng, Shuo Wang, Xin Zhao

Recently, large language models (LLMs) have shown remarkable reasoning abilities by producing long reasoning traces. However, as the sequence length grows, the key-value (KV) cache expands linearly, incurring significant memory and computation costs. Existing KV cache eviction methods mitigate this issue by discarding less important KV pairs, but often fail to capture complex KV dependencies, resulting in performance degradation. To better balance efficiency and performance, we introduce ForesightKV, a training-based KV cache eviction framework that learns to predict which KV pairs to evict during long-text generations. We first design the Golden Eviction algorithm, which identifies the optimal eviction KV pairs at each step using future attention scores. These traces and the scores at each step are then distilled via supervised training with a Pairwise Ranking Loss. Furthermore, we formulate cache eviction as a Markov Decision Process and apply the GRPO algorithm to mitigate the significant language modeling loss increase on low-entropy tokens. Experiments on AIME2024 and AIME2025 benchmarks of three reasoning models demonstrate that ForesightKV consistently outperforms prior methods under only half the cache budget, while benefiting synergistically from both supervised and reinforcement learning approaches. Code is available at \url{https://github.com/RUCAIBox/ForesightKV}.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.