New analysis shows interpretability doesn't guarantee steering utility in LLMs.
problem Does higher interpretability lead to better steering utility in large language models?
method Trained 90 SAEs across three LLMs, evaluated interpretability and steering utility, used Kendall's rank coefficients for analysis.
result Interpretability is only weakly associated with steering utility, and features selected by Delta Token Confidence improve steering performance.
New model shows most users on Q&A site Stack Overflow ignore badges.
problem Understanding user behavior in Q&A websites with badges.
method Probabilistic model applied to Stack Overflow data.
result Majority of users remain apathetic to badges but still contribute.
New approach extracts AI model representations for steering and monitoring.
problem Understanding and steering AI models' internal knowledge representation.
method Feature learning advances for scalable linear concept representations.
result Concept representations enable steering and monitoring of AI models.
New method steers protein design towards desired properties.
problem Challenges in designing proteins with specific structures and properties.
method Feynman-Kac framework applied to RFdiffusion models with guiding potentials.
result Significant improvement in predicted interface energetics and binder designability.
Study designs incentives for adapting multi-agent systems without knowing their learning dynamics.
problem Designing incentives for an adapting population in multi-agent systems without prior knowledge of their learning dynamics.
method Introduces a model-based non-episodic Reinforcement Learning (RL) formulation for steering Markovian agents towards desired policies, focusing on history-dependent strategies to handle model uncertainty.
result Identifies conditions for the existence of steering strategies to guide agents to desired policies and provides empirical algorithms to approximately solve the objective.
Study designs steering rewards for MFGs with unknown dynamics and model uncertainty.
problem Designing incentives for large populations of agents in MFGs with uncertain model details.
method Developed optimistic exploration algorithms for agents with no-adaptive regret behaviors.
result Sub-linear regret guarantees for cumulative gaps between agent behaviors and desired outcomes.
Painless Activation Steering automates post-training for LMs without manual intervention.
problem Manual post-training methods are time-consuming and labor-intensive.
method Painless Activation Steering (PAS) is a fully automated approach that requires no manual intervention.
result PAS reliably improves performance for behavior tasks but not for intelligence-oriented tasks.
Interactive steering improves hierarchical clustering for diverse user needs.
problem Existing hierarchical clustering methods fail to meet diverse user needs.
method Knowledge-driven and data-driven constraints, interactive steering through a visual interface.
result Facilitates the building of customized clustering trees efficiently and effectively.
Bayesian Power Steering fine-tunes large diffusion models for domain adaptation.
problem Fine-tuning pre-trained diffusion models for tasks in a smaller probability space.
method Bayesian framework with a novel network structure (Bayesian Power Steering).
result Bayesian Power Steering achieves an FID score of 10.49 on the COCO17 dataset.
New method prevents RLHF alignment collapse by accounting for policy's influence on reward model updates.
problem Iterative RLHF leads to alignment collapse where policies exploit RM's blind spots.
method Foresighted policy optimization (FPO) restores missing steering term via regularization.
result FPO prevents alignment collapse on LLM alignment pipelines using Llama-3.2-1B.
Unified Bayesian model explains in-context learning and activation steering in LLMs.
problem Understanding and controlling the behavior of large language models (LLMs) through prompts and activations.
method Developed a Bayesian model to explain and predict the effects of in-context learning and activation steering.
result Unified model predicts distinct phases and sudden shifts in LLM behavior, explaining prior empirical phenomena.
Self-driving vehicles have expanded dramatically over the last few years. Udacity has release a dataset containing, among other data, a set of images with the steering angle captured during driving. The Udacity challenge aimed to predict steering angle based on only the provided images. We explore two different models …
We show LLMs can be locally linear, enabling better control of activations.
problem Suboptimal control of LLM activations during generation.
method Model LLM inference as a linear dynamical system, compute feedback controllers using Jacobians, and adapt classical control theory.
result Robust, fine-grained control of LLM activations across models and tasks.
The paper explores how AI systems use information geometry to encode semantic structure.
problem How AI systems encode semantic structure into geometric representation spaces.
method Focuses on softmax distributions and develops dual steering method for robust concept manipulation.
result Dual steering optimally modifies target concepts while minimizing off-target changes.
ELS framework improves safety alignment by dynamically steering LLMs towards helpful responses.
problem Over-Refusal in Aligned Large Language Models
method Fine-tuning free framework using an Energy-Based Model (EBM) to dynamically steer LLMs during inference.
result Extensive experiments show a significant reduction in false refusals (from 57.3% to 82.6%) while maintaining safety performance.
NAS-Navigator automates neural network architecture search with visual steering.
problem Difficulty in configuring large neural networks efficiently.
method Formulates architecture optimization as graph space exploration, trains all candidate architectures in one-shot.
result Allows analysts to effectively select and guide the search for optimal neural network architectures.
Increased data gathering capacity, together with the spread of data analytics techniques, has prompted an unprecedented concentration of information related to the individuals' preferences in the hands of a few gatekeepers. In the present paper, we show how platforms' performances still appear astonishing in relation t…
Solves steering problem with continuous time, Hilbert-Schmidt cost, and matrix ODEs.
problem Fixed horizon linear quadratic covariance steering in continuous time with a specific terminal cost.
method Formulates necessary conditions as a coupled matrix ODE two-point boundary value problem, designs a matricial recursive algorithm, and proves convergence.
result Proposes and proves the convergence of a matricial recursive algorithm for solving the steering problem.
User engagement in online social networking depends critically on the level of social activity in the corresponding platform--the number of online actions, such as posts, shares or replies, taken by their users. Can we design data-driven algorithms to increase social activity? At a user level, such algorithms may incre…
A new method steers Gaussian distributions with minimal effort.
problem Steering high-dimensional Gaussian distributions efficiently.
method Sliced feedback controller using one-dimensional projections and averaging.
result The method steers Gaussian distributions to targets efficiently.
This paper improves model training by using a reference model to guide target model training.
problem Improving generalization and data efficiency in model training.
method DRRho risk minimization framework based on Distributionally Robust Optimization (DRO).
result DRRho risk minimization improves generalization and data efficiency compared to training without a reference model.
A new method for steering large agent populations efficiently.
problem Controlling the configuration of a swarm of identical, interacting cooperative agents.
method Mean-Field Schrodinger Bridges with Gaussian Mixture Models.
result A highly efficient parameterization to approximate optimal solutions of the MFSB problem in closed form.
Model-free reinforcement learning has recently been shown to successfully learn navigation policies from raw sensor data. In this work, we address the problem of learning driving policies for an autonomous agent in a high-fidelity simulator. Building upon recent research that applies deep reinforcement learning to navi…
MFMs enable efficient reward alignment for generative models.
problem Computational bottleneck in controlling generative models.
method Meta Flow Maps (MFMs) extend consistency models and flow maps to stochastic regime for efficient value function estimation.
result MFMs enable inference-time steering and unbiased, off-policy fine-tuning to general rewards efficiently.
New benchmark uncovers hidden biases in LLMs that refuse to answer certain queries.
problem Evaluating fairness in LLMs, especially in sensitive applications.
method Silenced Bias Benchmark (SBB) using activation steering to reduce model refusals during QA.
result Exposes hidden unfair preferences in LLMs' latent space, distinguishing direct responses from underlying fairness issues.
Signed-permutation coordinate transport improves model alignment across checkpoints.
problem Improper alignment of coordinate-indexed objects across model checkpoints.
method Introduces sign-marginalized Hungarian matching and coordinate-preserving transport.
result Recovering signed-permutation gauge improves coordinate alignment and model performance.
Regularization improves stability and consistency of sparse autoencoders.
problem Varying features across random seeds and training choices in SAEs.
method Added L1 or L2 penalties on encoder and decoder weights.
result L2 regularization increases cross-seed feature consistency.
End-to-end autonomous driving models get better uncertainty estimates.
problem Uncertainty quantification for end-to-end autonomous driving models.
method Approximate inference for implicit copula neural linear model.
result Densities for steering angle are marginally calibrated.
The paper explores linear representations in language models using counterfactuals.
problem Understanding linear representations and geometric concepts in large language models.
method Formalized linear representation in output and input spaces, identified causal inner product.
result Unified understanding of linear representations and their connection to interpretation and control.
Unified framework for image classification and regression using cGAN-generated samples.
problem Lack of unified KD methods for both classification and regression tasks.
method cGAN-KD framework based on cGANs.
result Unified framework for both classification and regression tasks, compatible with other KD methods.
Computer science scans LLMs to understand and manipulate their economic forecasts.
problem Understanding and controlling the reasoning of large language models in economics.
method Brain scanning techniques applied to LLMs to identify and manipulate underlying concepts.
result LLMs can be steered to generate forecasts with specific biases, allowing for correction or simulation.
Deep RL optimizes sensor placement in digital twins for dynamic data acquisition.
problem Limited applicability of traditional sensor placement techniques for online applications.
method Formulates sensor placement as a Markov decision process and uses deep reinforcement learning.
result Improves predictive accuracy and reliability of digital twins through adaptive sensor repositioning.
A novel controller for wheeled robots handles joystick inputs for smooth steering.
problem Steering control for differential-drive wheeled robots from indirect joystick inputs.
method Developed a geometric controller based on Darboux frame kinematics.
result Smooth trajectories achieved with safety constraints and no desired states.
FlowChef steers RFMs to efficiently guide image generation tasks.
problem Efficiently guiding image generation tasks with RFMs.
method Developed a theoretical and empirical understanding of RFMs' vector field dynamics, proposing FlowChef for gradient-free navigation.
result FlowChef significantly outperforms baselines in performance, memory, and time requirements.
New method adapts to user preferences dynamically, improving recommendation models.
problem Current recommendation models lack dynamic adaptation to changing user preferences.
method Preference Discerning with LLM-Enhanced Generative Retrieval
result Mender achieves state-of-the-art performance in adapting to evolving user preferences.
OBJECTIVE: We aim to extract and denoise the attended speaker in a noisy, two-speaker acoustic scenario, relying on microphone array recordings from a binaural hearing aid, which are complemented with electroencephalography (EEG) recordings to infer the speaker of interest. METHODS: In this study, we propose a modular …
Deep Neural Networks (DNNs) have tremendous potential in advancing the vision for self-driving cars. However, the security of DNN models in this context leads to major safety implications and needs to be better understood. We consider the case study of steering angle prediction from camera images, using the dataset fro…
This work examines the role of reinforcement learning in reducing the severity of on-road collisions by controlling velocity and steering in situations in which contact is imminent. We construct a model, given camera images as input, that is capable of learning and predicting the dynamics of obstacles, cars and pedestr…
In application domains such as healthcare, we want accurate predictive models that are also causally interpretable. In pursuit of such models, we propose a causal regularizer to steer predictive models towards causally-interpretable solutions and theoretically study its properties. In a large-scale analysis of Electron…
One of the important theorems in homotopy theory is the Hilton splitting. In this paper we will construct all the Hilton homomorphisms by geometrical means and prove a family of sharper symmetry relations of linking coefficients which desuspend and generalize the relations of Kervaire, Haefliger and Steer.
A novel hierarchical Deep Neural Network (DNN) model is presented to address the task of end-to-end driving. The model consists of a master classifier network which determines the driving task required from an input stereo image and directs said image to one of a set of subservient network regression models that perfor…
Optimally explores dynamical systems with varying properties using context inference.
problem Learning dynamics models for systems with varying properties.
method Formulates dynamics models as stochastic processes conditioned on a latent context variable inferred from system transitions. Uses probabilistic formulation to compute optimal action sequences for exploration.
result Demonstrates effectiveness of the method on non-linear toy-problems and reinforcement learning environments.
Small, carefully crafted perturbations called adversarial perturbations can easily fool neural networks. However, these perturbations are largely additive and not naturally found. We turn our attention to the field of Autonomous navigation wherein adverse weather conditions such as fog have a drastic effect on the pred…
Storytelling algorithms aim to 'connect the dots' between disparate documents by linking starting and ending documents through a series of intermediate documents. Existing storytelling algorithms are based on notions of coherence and connectivity, and thus the primary way by which users can steer the story construction…
Self-guidance controls image generation by extracting properties from diffusion model representations.
problem Generating images from text descriptions is challenging due to the complexity of visual details.
method Self-guidance uses internal representations of diffusion models to control image generation.
result Properties like object shape, location, and appearance can be extracted and used to steer image generation.
Exact guidance for discrete data improves posterior sampling efficiency.
problem Inefficient guidance for discrete data in posterior sampling.
method Derive exact transition rate for desired distribution given learned discrete flow matching model.
result Significantly improved efficiency with single forward pass per sampling step.
A simple regularization technique speeds up training of Neural ODEs.
problem Training Neural ODEs is computationally expensive.
method Randomly sampling the end time of the ODE during training.
result Significantly decreases training time and improves performance.
New algorithm solves Schrödinger bridge problem with mismatched channels.
problem Solving Schrödinger bridge problem with input and noise channel mismatch.
method Design of a Sinkhorn recursion with memory for nonlinear PDEs.
result Demonstrates solving control-affine Schrödinger bridge problem.