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.

ICML 2026

Edge-colored Clustering in Hypergraphs: A MaxECC Approximation

Aravind Srinivasan, Arushi Srinivasan, Jiayi Wu

We study the MaxECC problem, where given an edge-colored hypergraph with $k$ colors and edge size $r$, we seek to color the vertices of the graph in order to maximize the number of satisfied edges (edges having the same color as their extremities): this is an effective mechanism for clustering (coloring) objects based on their multi-way interactions with one another in a system, providing significant applications in machine learning, clustering, and data mining. We exponentially improve upon the approximation ratio of an existing algorithm to $\frac{1}{r+1}$, present another novel dependent-rounding algorithm with an approximation ratio of $1/ \lceil \frac{k}{2}\rceil$, and modify the initial algorithm via analytical scaling techniques in order to achieve an approximation factor of $(1-e^{-r})/r$. We then apply our scaling algorithm to graph MaxECC and improve the best-known approximation factor for all hypergraphs: in particular, our algorithm provides an approximation factor of $0.43$ as opposed to the previously-known $0.38$ factor for graphs.

ICML 2026

TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting

Quang Duc Nguyen, Siyuan Liang, Yiming Li, Fushuo Huo, Dacheng Tao

Time Series Forecasting (TSF) is highly vulnerable to backdoor attacks, yet effective defenses remain underexplored due to challenges arising from data entanglement and shifts in task formulation. To fill this gap, we conduct a systematic evaluation of thirteen representative backdoor defenses across the TSF life cycle and analyze their failure modes. Our results reveal two fundamental issues: (1) data entanglement induces *channel-level signal dilution*, rendering sample-filtering and trigger-synthesis defenses ineffective at localizing backdoors; and (2) task-formulation shift leads to *training-loss degeneration*, causing poisoned and clean windows to become indistinguishable at training stages. Based on these findings, we propose a training-time backdoor defense for TSF, termed TimeGuard. Our method adopts channel-wise pool training as the core paradigm and initializes a high-confidence pool using time-aware criteria to mitigate signal dilution. Moreover, we introduce distance-regularized loss selection to progressively expand the reliable pool during training and ease loss degeneration. Extensive experiments across multiple datasets, forecasting architectures, and TSF backdoor attacks demonstrate that TimeGuard substantially improves robustness, boosting $\mathrm{MAE}_ \mathrm{P}$ by $1.96\times$ over the leading baseline, while preserving clean performance within 5% $\mathrm{MAE}_ \mathrm{C}$.

ICML 2026

Complexity of Decentralized Optimization with Mixed Affine Constraints

Demyan Yarmoshik, Nhat Trung Nguyen, Alexander Rogozin, Alexander Gasnikov

This paper considers decentralized optimization of convex functions with mixed affine equality constraints involving both local and global variables. Constraints on global variables may vary across different nodes in the network, while local variables are subject to coupled and node-specific constraints. Such problem formulations arise in machine learning applications, including federated learning and multi-task learning, as well as in resource allocation and distributed control. We analyze this problem under smooth and non-smooth assumptions, considering both strongly convex and general convex objective functions. Our main contribution is an optimal algorithm for the smooth, strongly convex regime, whose convergence rate matches established lower complexity bounds. We further provide optimal and near-optimal methods for the remaining cases.

ICML 2026

LiME: Lightweight Mixture of Experts for Efficient Multimodal Multi-task Learning

Md Kowsher, Haris Mansoor, Nusrat Jahan Prottasha, Ozlem Garibay, Victor Zhu, Zhengping Ji, Chen Chen

MoE-PEFT methods combine Mixture of Experts with parameter-efficient fine-tuning for multi-task adaptation, but require separate adapters per expert—causing trainable parameters to scale linearly with expert count and limiting applicability to adapter-based architectures. We propose LiME (Lightweight Mixture of Experts), which achieves expert specialization through lightweight modulation rather than adapter replication. Instead of separate adapters, LiME uses a single shared PEFT module and modulates its output with lightweight expert vectors, reducing expert parameters while generalizing to any PEFT method. Notably, LiME introduces zero-parameter routing by leveraging existing frozen and adapted representations—eliminating learned router parameters typically required per layer. Theoretically, we prove that (i) more experts preserve more task-relevant information and (ii) modulation approximates full expert-specific PEFT with bounded error. LiME further incorporates n-gram windowed routing and adaptive expert selection (Auto Top-K) based on routing confidence. Experiments on MMT-47, a multimodal multi-task benchmark with 47 tasks spanning text, image, and video, demonstrate that LiME achieves competitive or superior performance while using up to 4× fewer trainable parameters and up to 29% faster training compared to corresponding MoE-PEFT baselines.

ICML 2026

MaMa: A Game-Theoretic Approach for Designing Safe Agentic Systems

Jonathan Nöther, Adish Singla, Goran Radanovic

LLM-based multi-agent systems have demonstrated impressive capabilities, but they also introduce significant safety risks when individual agents fail or behave adversarially. In this work, we study the automated design of agentic systems that remain safe even when a subset of agents is compromised. Inspired by Stackelberg security games, we formalize this problem as a game between a system designer (the Meta-Agent) and a best-responding Meta-Adversary that selects and compromises a subset of agents to minimize safety. We propose Meta-Adversary–Meta-Agent (MaMa), a novel algorithm inspired by this formalization for automatically designing safe agentic systems. Our approach uses LLM-based adversarial search, where the Meta-Agent iteratively proposes system designs and receives feedback based on the strongest attacks discovered by the Meta-Adversary. Empirical evaluations across diverse environments show that systems designed with MaMa consistently defend against worst-case attacks while maintaining performance comparable to systems optimized solely for task success. Moreover, the resulting systems generalize to stronger adversaries, as well as ones with different attack objectives or underlying LLMs, demonstrating robust safety beyond the training setting. Code is available at https://github.com/JNoether/MaMa

ICML 2026

Learning to Move Before Learning to Do: Task-Agnostic pretraining for VLAs

Junhao Shi, Siyin Wang, Xiaopeng Yu, Li Ji, Jingjing Gong, Xipeng Qiu

Vision-Language-Action (VLA) models are bottlenecked by the scarcity of expert demonstrations—expensive triplets of observations, language instructions, and actions. We propose that learning ''how to move'' can be decoupled from learning ''what to do,'' and that the former requires no task labels at all. Our two-stage framework, **Task-Agnostic Pretraining (TAP)** first pre-trains on abundant, cheap *task-agnostic* data (discarded off-task trajectories or autonomous robot play) using an Inverse Dynamics objective that predicts actions from consecutive observations. This self-supervised phase instills physical affordances—grasping, contact dynamics, end-effector control—without human annotation. A lightweight second stage then aligns these physical priors with language instructions using minimal expert data. On the SIMPLER benchmark, our approach matches models trained on 1M+ expert trajectories while using orders of magnitude less labeled data, achieving a 10\% absolute gain over standard behavior cloning. In real-world WidowX experiments, it surpasses internet-scale baselines under visual distribution shifts (e.g., 25\% vs. 0\% under camera perturbations), demonstrating that task-agnostic pretraining yields robust, transferable physical representations for Embodied AI.

ICML 2026

JADE: Bridging the Strategic-Operational Gap in Dynamic Agentic RAG

Yiqun Chen, Erhan Zhang, Tianyi Hu, Shijie Wang, Zixuan Yang, Meizhi Zhong, Xiaochi Wei, Yan Gao, Yi Wu, Yao Hu, Jiaxin Mao

The evolution of Retrieval-Augmented Generation (RAG) has shifted from static retrieval pipelines to dynamic, agentic workflows where a central planner orchestrates multi-turn reasoning. However, existing paradigms face a critical dichotomy: they either jointly optimize modules within rigid, fixed-graph architectures, or enable dynamic planning while treating executors as frozen, black-box tools. We identify that this \textit{decoupled optimization} creates a ``strategic-operational mismatch,'' where sophisticated planning strategies fail to materialize due to unadapted local executors, often causing negative gains despite increased system complexity. In this paper, we propose \textbf{JADE} (\textbf{J}oint \textbf{A}gentic \textbf{D}ynamic \textbf{E}xecution), a unified framework for joint optimization of planning and execution within dynamic, multi-turn workflows. By modeling the system as a cooperative multi-agent team with a shared backbone, JADE enables end-to-end learning driven by outcome-based rewards. This approach facilitates \textit{co-adaptation}: the planner learns to operate within executor capability boundaries, while executors evolve to align with strategic intent. Empirical results demonstrate that JADE transforms disjoint modules into a synergistic system, yielding strong performance improvements via joint optimization and enabling a flexible balance between efficiency and effectiveness through dynamic workflow orchestration.

ICML 2026

Salus: Strategic Diagnostic Testing for Complex Diagnosis via Multi-Agent Reinforcement Learning

Shuohao Gao, Xuanzhong Chen, Lingxiao Luo, Zilin Ding, Rong Han, Rui Jiang, Ting Chen

Diagnosing complex diseases is inherently a sequential and iterative medical investigation process, in which a clinician strategically requests multiple rounds of diagnostic tests to differentiate among similar diseases until reaching a definitive diagnosis. Although large language models show great potential as clinical assistants, they often struggle to navigate this complex interactive process, suffering from premature diagnostic closure. Furthermore, optimizing LLMs for such multi-round environments is frequently hindered by the challenge of reward sparsity and hacking. In this paper, we introduce $\textbf{CompDiag-Bench}$, a benchmark that formalizes diagnosis as a sequential decision-making process where a clinician must strategically request diagnostic tests from a dynamic environment in order to reach a definitive diagnosis. To address this task, we propose $\texttt{Salus}$, a multi-agent framework that decouples diagnostic reasoning into three specialized functional roles: a Differential Reasoner, a Strategic Controller, and a Workup Proposer. $\texttt{Salus}$ is optimized via multi-agent reinforcement learning employing structured rewards to calibrate strategic diagnostic behavior. Specifically, we leverage an LLM-as-a-Judge reward mechanism to provide dense, semantically-grounded feedback, designed to penalize premature closure and incentivize accurate differential diagnoses. Experimental results show that our model, $\texttt{Salus-7B}$, attains state-of-the-art Top-1 accuracy of $83.64\%$ on complex cases, outperforming DeepSeek-V3.2 ($71.38\%$) and achieving performance on par with GPT-5.2 ($80.30\%$).

ICML 2026

Accelerated Dual Method for Distributed Optimization: An Inexact-Gradient View of Local Updates

Junchi YANG, Ziyang Zeng, Pan Linxuan, Murat Yildirim, Feng Qiu

In distributed machine learning, efficiently training across multiple agents with heterogeneous data distributions remains a central challenge. We address the problem of stochastic, strongly convex distributed optimization by applying accelerated gradient ascent to the dual variables and multi-step stochastic gradient descent (SGD) to the primal variables in the Lagrangian formulation. This approach naturally enables local computation, as the inner SGD loops require no inter-agent communication. We prove that the method converges for any number of local updates, attaining the optimal communication complexity when local computation is sufficient. Our analysis builds on an inexact accelerated gradient framework, where the partial gradient of the Lagrangian with respect to the dual variables is treated as an inexact gradient of the dual function. A notable byproduct of this framework is an algorithm that achieves optimal reproducibility guarantees under biased gradient estimates.

ICML 2026

Amortized Variational Inference for Partial-Label Learning: A Probabilistic Approach to Label Disambiguation

Tobias Fuchs, Nadja Klein

Real-world data is frequently noisy and ambiguous. In crowdsourcing, for example, human annotators may assign conflicting class labels to the same instances. Partial-label learning (PLL) addresses this challenge by training classifiers when each instance is associated with a set of candidate labels, only one of which is correct. While early PLL methods approximate the true label posterior, they are often computationally intensive. Recent deep learning approaches improve scalability but rely on surrogate losses and heuristic label refinement. We introduce a novel probabilistic framework that directly approximates the posterior distribution over true labels using amortized variational inference. Our method employs neural networks to predict variational parameters from input data, enabling efficient inference. This approach combines the expressiveness of deep learning with the rigor of probabilistic modeling, while remaining architecture-agnostic. Theoretical analysis and extensive experiments on synthetic and real-world datasets demonstrate that our method achieves state-of-the-art performance in both accuracy and efficiency.

ICML 2026

You Don't Protect if You Don't Expect: Breaking the Key Assumption behind CLIP's Test-Time Defenses

Ruize Zhang, Yu Li, Zhang Wan, Juan Cao, Jie Zhang, Sheng Tang

Recent test-time defenses for CLIP claim to preserve zero-shot clean accuracy while improving adversarial robustness. However, we find the reported robustness of six recent proposed state-of-the-art methods substantially overestimated: they fail under basic adaptive attacks. We further observe that these defenses share a common reliance on an indicative measurement that is assumed to capture the distributional difference between clean and adversarial samples and to determine whether the defense should preserve or alter the static model's prediction. We argue that this assumption is the fundamental weakness, and we propose CLIP-MAD (Manipulating Assumed Difference), an adaptive attack strategy designed to break it. CLIP-MAD efficiently expands the adversarial distribution without costly full gradient calculations and can be flexibly combined with existing attack baselines to further boost attack strength. Experiments across 13 datasets demonstrate that CLIP-MAD produces strong adversarial samples that markedly reduce the robustness of diverse test-time defenses, revealing a false sense of security in CLIP’s zero-shot robustness. Code will be available at https://github.com/rzzhang222/CLIP-MAD.

ICML 2026

TadA-Bench: A Million-Variant Benchmark for Future-Round Discovery Toward Agentic Protein Engineering

Jin Gao, Juntu Zhao, Zirui Zeng, Jiaqi Shen, Junhao Shi, Dukun Zhao, Yuming Lu, Dequan Wang

AI for scientific discovery is entering an agentic era, where protein-engineering systems are expected to prioritize future wet-lab experiments rather than merely fit static measurements. We introduce TadA-Bench, a million-variant wet-lab replay benchmark from 31 TadA directed-evolution rounds for future-round discovery toward agentic protein engineering. TadA-Bench preserves the campaign chronology and defines a fixed-data replay task: given earlier experimental rounds, models rank variants that appear only in later rounds. It provides aligned DNA, RNA, and protein views, and uses Seq2Graph, a graph-based label-unification pipeline, to reconcile noisy enrichment measurements into consistent cross-round activity labels. Random-split controls show strong interpolation, but future-round ranking and finite-budget candidate selection are much weaker. Controlled analyses suggest that evolutionary coverage is more informative than local data density, positioning TadA-Bench as a reproducible wet-lab replay substrate for future-round discovery toward agentic protein engineering; the data and code are released on Hugging Face and GitHub.

ICML 2026

Speech-Audio Compositional Attacks on Multimodal LLMs and Their Defense with SALMONN-Guard

Yudong Yang, Xuezhen Zhang, Zhifeng Han, Siyin Wang, Jimin Zhuang, Zengrui Jin, Jing Shao, Guangzhi Sun, Chao Zhang

Recent progress in large language models (LLMs) has enabled understanding of both speech and non-speech audio, but has also exposed new safety risks arising from complex audio inputs that are inadequately handled by current safeguards. We introduce SACRED-Bench (Speech–Audio Composition for RED-teaming) to evaluate the robustness of LLMs under complex audio-based attacks. Unlike existing perturbation-based methods that rely on noise optimization or white-box access, SACRED-Bench exploits speech–audio composition to enable effective black-box attacks. SACRED-Bench adopts three composition mechanisms: (a) speech overlap, (b) multi-speaker dialogue, and (c) mixtures of speech and non-speech audio. These mechanisms focus on evaluating safety in settings where benign and harmful intents co-occur within a single auditory scene. Moreover, questions in SACRED-Bench are designed to implicitly refer to content in the audio, such that no explicit harmful information appears in the text prompt alone. Experiments demonstrate that even Gemini 2.5 Pro, a state-of-the-art proprietary LLM with safety guardrails fully enabled, still exhibits a 66% attack success rate. To bridge this gap, we propose SALMONN-Guard, the first guard model that jointly inspects speech, audio, and text for safety judgments, reducing the attack success rate to 20\%. Our results highlight the need for audio-aware defenses to ensure the safety of multimodal LLMs.

ICML 2026

The Geometry of Sequential Learning: Lie-Bracket Prediction of Transfer Order

John Sweeney

Sequential learning is order-dependent: from Pile-style next-token domain adaptation to instruction-SFT and DPO, $N$ candidate sources induce $N!$ possible curricula. We show that the local order effect is governed by a computable geometric quantity, the Lie-bracket commutator of gradient update fields, yielding a pairwise score for whether $A \to B$ or $B \to A$ is better for a target domain. The pairwise bracket primitive also defines a *Lie-Bracket Tournament*: with a shared $\theta_0$ target-gradient reference, Hessian symmetry gives Borda/row-sum scores from one Hessian-vector product per source, $O(N)$ dot products, and an $O(N\log N)$ sort, without materializing the $O(N^2)$ edge matrix. Empirically, the planner reaches 98.1%/98.9% pairwise accuracy at $k=1$ for instruction-SFT/DPO, remains at 73.1%/72.2% at $k=20$, and preserves the original pretraining-domain evidence with 82.4–92.0% accuracy across four LLMs and 91.1% on diffusion. At curriculum scale, it recovers the best of all $3!$ schedules in 87.5% of trials, ranks 85 Stack programming-language source domains for a Python target in the 99th sampled percentile, and reaches the 99.0–99.6th sampled percentile on 56 MMLU subjects, sharply above the reported descending gradient-norm baseline. These results reframe sequential learning as a geometric tournament problem: commutators provide both local pairwise order information and a scalable primitive for many-domain schedules.

ICML 2026

DiffCrossGait: Trajectory-Level Alignment for 2D-3D Cross-Modal Gait Recognition via Latent Diffusion

Zhiyang Lu, Ming Cheng

Cross-modal 2D–3D gait recognition is impeded by inherent domain discrepancies between 2D silhouette and 3D point cloud distributions. While prior methods align only final embeddings, we propose DiffCrossGait, which enforces trajectory-level alignment by driving both modalities with shared noise in a unified latent diffusion process. By driving both modalities with shared Gaussian noise within a latent space, we enable continuous alignment throughout the generative evolution. We introduce a Tri-Phase Alignment Strategy that exploits varying noise intensities to enforce identity anchoring, dynamics consistency, and cross-modal structural recoverability, thereby constraining both modalities to share denoising dynamics and bottleneck structure, which promotes modality-invariant gait features. Crucially, our framework decouples generative alignment from the discriminative backbone; the diffusion mechanism serves exclusively as a training objective, ensuring high inference efficiency by eliminating the computational overhead of iterative denoising. Extensive experiments on the SUSTech1K and FreeGait benchmarks demonstrate that DiffCrossGait achieves state-of-the-art performance.

ICML 2026

Let the Prototype Guide You: Robust Aggregation of Sparse Multi-Class Annotations via Annotator Prototype Learning

Ju Chen, Jun Feng, Shenyu Zhang

Truth inference is a critical technique for aggregating noisy and biased multi-class classification annotations. State-of-the-art approaches model each annotator using an individual confusion matrix. While well-grounded, they suffer from two fundamental bottlenecks: 1) confusion matrices are underfit when annotators label only a small subset of tasks or when classes are imbalanced, and 2) a single confusion matrix per annotator is inadequate for capturing complex annotator behaviors, leading to class-level collapse when tasks are extremely difficult. Simultaneously addressing these challenges is non-trivial, as it demands both robustness to data sparsity and sufficient expressiveness for complex annotator patterns. In this paper, we propose \textbf{CPBCC} (\textbf{C}lass-specific \textbf{P}rototype-driven \textbf{B}ayesian \textbf{C}lassifier \textbf{C}ombination), which creatively models annotators through a dual-pathway architecture: (i) learning class-specific prototype annotation patterns across all annotators, and (ii) learning annotator-specific weights over prototypes. This framework addresses the bottlenecks and achieves a robust yet rich annotator characterization. Experiments across 10 real-world datasets spanning five domains demonstrate that CPBCC yields a 26\% accuracy improvement in the best case, and boosts average accuracy from 68.73\% to 74.11\%. Our source code is available at \url{https://github.com/JuJuCHEN-HHU/CPBCC_PTBCC}.

ICML 2026

X-MoGe: A Cross-Modal Adaptation Framework with Mixture-of-Experts and Geometry Guidance for Heterogeneous Collaborative Perception

Wenkai Lin, Zhihong Liu, Chenglu Wen

Multi-agent collaborative perception improves perception range and robustness in autonomous driving. However, most existing methods assume homogeneous sensors and perception networks, which is unrealistic in real-world heterogeneous systems. Differences in sensing modalities and independently trained models lead to significant semantic and geometric inconsistencies, limiting effective collaboration. To solve these problems, we propose a novel cross-modal adaptation framework with Mixture-of-Experts and geometry-guided fusion for heterogeneous collaborative perception, named X-MoGe. Specifically, we propose a Pixel-level Mixture-of-Experts (P-MoE) module, which adaptively models modality-specific semantic characteristics under heterogeneous sensing conditions. In addition, a geometry-guided feature fusion module incorporates explicit geometric priors to enforce spatial alignment and consistency in the BEV space. Extensive experiments on OPV2V and DAIR-V2X datasets demonstrate that the proposed method achieves state-of-the-art performance in heterogeneous collaborative perception.

ICML 2026

Data-Source Adaptive Online Learning under Heteroscedastic Noise

Amith Bhat Hosadurga Anand, Haipeng Luo, Aadirupa Saha

In this paper, we address the standard $K$-armed multi-armed bandit (MAB) with heterogeneous data sources, each exhibiting unknown and distinct noise variances, $\lbrace \sigma_j^2 \rbrace_{j=1}^{M}$. The learner performs standard regret minimization, with the added challenge of choosing which data source to query at each round. We propose SOAR (Source-Optimistic Adaptive Regret minimization), a novel algorithm that adaptively balances exploration and exploitation by jointly constructing upper confidence bounds for arm rewards and lower confidence bounds for data source variances. Our theoretical analysis establishes that SOAR achieves a regret bound of $\tilde{O}\left({\sigma^\star}^2 \sum_{i=2}^K \tfrac{1}{\Delta_i}\right),$ along with a preprocessing cost that depends only on the problem parameters $\lbrace \sigma_j \rbrace_{j=1}^{M}$, $K$, and grows at most logarithmically with the horizon $T$; where ${\sigma^\star}^2$ is the minimum source variance, and $\Delta_i$ denotes the suboptimality-gap of the $i$-th arm reward. The $\tilde{O}(\cdot)$ notation hides the polylogarithmic factors in these problem parameters. Notably, despite not knowing the minimum-variance source, SOAR matches the instance-dependent regret of a standard MAB run on a single source of variance $\sigma^\star$. This near-optimal instance-dependent regret analysis of SOAR underscores its effectiveness in dynamically managing heteroscedastic noise without incurring significant overhead. Experiments on synthetic problem instances as well as a real dataset (MovieLens 32M) demonstrate that our method significantly outperforms baseline bandit algorithms in terms of regret performance. Our work opens a new direction for adaptively leveraging multiple heterogeneous data sources, extending beyond traditional bandit frameworks.

ICML 2026

KUMA: A Novel Framework with Koopman Separation and Efficient Multilevel Extraction in Time Series Forecasting

Sijie Xiong, Cheng Tang, Atsushi Shimada

Time series forecasting plays a crucial role in a wide range of real-world applications and has become increasingly complex with the growth of multivariate dimensions and extended historical observations, leading to the prosperity of deep forecasting models. Previous models are hindered by three major challenges: high computational complexity, inefficient token utilization caused by redundancy and scarcity, and temporal distribution shifts resulting from non-stationary dynamics. Inspired by Koopman theory and the success of multilevel encoder–decoder architectures with skip connections, we design an input-dependent Koopman module to decompose time series into Koopman dynamics and residual dynamics. Building upon this formulation, we propose a U-shaped Multilevel Attention module (UMA) that integrates element-wise attention filtering and linear attention, giving rise to KUMA. The input-dependent Koopman operator mitigates the issue of operator mixture and alleviates temporal distribution shifts, while UMA achieves a favorable balance between token redundancy and token scarcity with acceptable computational efficiency. Comprehensive evaluations across 12 benchmark datasets demonstrate that KUMA achieves superior performance compared to existing excellent approaches.

ICML 2026

Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control

Julian Skifstad, Xinyue Annie Yang, Glen Chou

Inference-time LLM alignment methods, particularly activation steering, offer an alternative to fine-tuning by directly modifying activations during generation. Existing methods, however, often rely on non-anticipative interventions that ignore how perturbations propagate through transformer layers and lack online error feedback, resulting in suboptimal, open-loop control. To address this, we show empirically that layer-wise dynamics across multiple LLM architectures and scales are well-approximated by locally-linear models, despite the nonlinear structure of transformer blocks. Exploiting this property, we model LLM inference as a linear time-varying dynamical system and adapt the classical linear quadratic regulator to compute feedback controllers using layer-wise Jacobians, steering activations toward desired semantic setpoints in closed-loop with minimal computational overhead and no offline training. We also derive theoretical bounds on setpoint tracking error, enabling formal guarantees on steering performance. Using a novel adaptive semantic feature setpoint signal, our method yields robust, fine-grained behavior control across models, scales, and tasks, including state-of-the-art modulation of toxicity, truthfulness, refusal, and arbitrary concepts, surpassing baseline steering methods.

Keep browsing

More papers from top AI conferences

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