Compact binary CNNs improve landmark localization on limited resources.
problem Designing lightweight architectures for landmark localization with limited resources.
method Binarization of neural networks, hierarchical, parallel, multi-scale residual architecture.
result Significant performance improvement over standard architectures.
Synthesizes faces from facial features, invariant to pose and expression.
problem Creating realistic face images from facial features.
method Learning facial landmarks and textures from facial-recognition features, training on frontal, neutral-expression images.
result Generated images are invariant to lighting, pose, and expression.
Enhances curve alignment for diverse data types.
problem Aligning curve data effectively.
method Developed nonlinear transformations for curve data.
result Successfully aligned synthetic and real curve data.
Generates high-resolution faces based on attributes.
problem Creating realistic face images with user-specified attributes.
method Conditional CycleGAN, handling unpaired data and attribute control.
result Produces realistic face images with user-controlled attributes.
Solves reinforcement learning reward design for user-aligned agents.
problem Designing effective reward functions for reinforcement learning.
method Reward modeling: learn from user interaction and optimize.
result Agents can be aligned with user intentions through learned reward functions.
A new method reduces preference distortion in LLM alignment.
problem Vulnerability of traditional LLM alignment methods to human preference heterogeneity.
method Sign Estimator: A simple, provably consistent, and efficient estimator using binary classification loss.
result Substantially reduces preference distortion over a panel of simulated personas.
WiFi helps align and calibrate foot-mounted IMU trajectories.
problem Inertial drift and unknown initial states in FMIP.
method Graph-based SLAM with RSS measurements for WiFi APs.
result Aligns and calibrates trajectories accurately.
New method distills cloud models into edge-friendly ones.
problem Cloud-to-edge model compression with limited data exchange.
method Two-step workflow of deprivatization and distillation.
result Outperforms previous state-of-the-art approaches on various benchmarks.
New framework formalizes RLHF trilemma: improving safety, fairness, and robustness is computationally infeasible.
problem Aligning large language models with diverse human values while maintaining computational feasibility and robustness.
method Complexity-theoretic analysis integrating statistical learning theory and robust optimization.
result Achieving both representativeness (epsilon <= 0.01) and robustness (delta <= 0.001) for global-scale populations requires super-polynomial operations.
Robust high-dimensional data processing has witnessed an exciting development in recent years, as theoretical results have shown that it is possible using convex programming to optimize data fit to a low-rank component plus a sparse outlier component. This problem is also known as Robust PCA, and it has found applicati…
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.
PAC-Bayesian theory improves text-to-image models by enforcing alignment and generalization.
problem Text-to-image models struggle with complex prompts, misaligning modifiers and neglecting certain elements.
method Proposes a Bayesian approach with custom priors over attention distributions to enforce desirable properties.
result Achieves state-of-the-art results across multiple metrics on standard benchmarks.
New algorithm improves inference-time alignment without reward hacking.
problem Improving quality of responses from language models with limited compute.
method Inference-time alignment, focusing on extttInferenceTimePessimism algorithm. result Optimal performance and scaling-monotonicity of extttInferenceTimePessimism. A3RL combines online and offline RL with active sampling to improve policy learning.
problem Combining online and offline RL for sample efficiency and robustness.
method A3RL uses a confidence-aware Active Advantage Aligned (A3) sampling strategy to prioritize data from both online and offline sources.
result A3RL outperforms competing online RL techniques that use offline data.
Unified framework for efficient online training of RNNs.
problem Efficient and biologically plausible online training of recurrent neural networks.
method Organizes algorithms based on criteria like past vs. future facing, tensor structure, stochastic vs. deterministic, and closed form vs. numerical.
result Algorithms cluster according to criteria, revealing conceptual connections.
New benchmark and COAL model tackle class-imbalanced domain adaptation.
problem Aligning feature and label distributions across domains with different label distributions.
method COAL model combining feature and label distribution alignment.
result COAL model outperforms recent domain adaptation methods.
DET unifies geometric and functional alignment for high-dimensional scientific data.
problem Challenges in nonrigid registration for high-dimensional, irregular data.
method Domain Elastic Transform (DET) treats data as functions on irregular domains, using a Bayesian framework for elastic motion registration.
result DET achieves 92% topological preservation on MERFISH data and successfully registers whole-embryo Stereo-seq atlases.
Study shows GDP and CPI predict CCC funding, highlighting need for economic forecasting.
problem Challenges in aligning CCC funding with DEI initiatives.
method Quantitative correlational design, analyzing 30 years of economic data.
result Strong positive correlation between GDP growth and CCC funding levels, and between CPI and funding levels.
A new deep generative model captures global dependencies without supervision.
problem Global modeling in deep generative models.
method Non-i.i.d. variational autoencoders with mixture model and global Gaussian latent variable.
result Captures interpretable disentangled representations and domain alignment.
NIFTY dataset for financial forecasting models.
problem Improving financial market forecasting with LLMs.
method Two datasets for supervised and reinforcement learning.
result Demonstrates applications in stock price prediction.
Enhances monitoring of industrial systems with limited data.
problem Early detection of rare faults in safety-critical systems with limited training data.
method Feature alignment techniques (variational encoder, adversarial training) to align features from different units.
result Feature alignment improves robustness of one-class classifier for health monitoring.
Study assesses linear classifiers for virus genotyping and subtyping.
problem Challenges in classifying viral sequences, especially in alignment-free methods.
method Comprehensive evaluation of linear classifiers on HCV genomes, varying parameters and sequence lengths.
result Several classifiers perform well under specific conditions, providing robust assessment.
The paper studies and mitigates accuracy disparity in regression models.
problem Accuracy disparity between different demographic subgroups in high-stakes domains.
method Error decomposition theorem and distribution alignment algorithm.
result The proposed algorithm effectively mitigates accuracy disparity while maintaining predictive power.
Optimal fees for G3Ms align LP value with market accuracy.
problem Optimal fees for G3Ms to attract liquidity without sacrificing accuracy.
method Developed a framework for determining LP value with fees for G3Ms under diffusion.
result LPs prefer G3Ms over other strategies as fees approach zero.
FSBM improves matching efficiency with minimal supervision.
problem Scalability vs. minimal supervision in matching frameworks.
method FSBM uses a small portion of pre-aligned pairs as state feedback to guide non-coupled samples.
result FSBM accelerates training and enhances generalization.
Federated learning framework improves model generalization and privacy.
problem Communication overhead and statistical heterogeneity in FL.
method Prototypes and lightweight adapters for local model refinement.
result Improves classification accuracy over baseline algorithms.
The paper characterizes functions of shallow ReLU NN denoisers under minimal norm constraints.
problem Understanding the theoretical success of neural network denoisers.
method Characterization of functions realized by shallow ReLU NN denoisers under minimal norm constraints.
result The functions realized by shallow ReLU NN denoisers are contractive toward clean data points and generalize better than the empirical MMSE estimator at low noise levels.
SIGL learns scalable graphons from graphs.
problem Estimating graphons from graphs of varying sizes.
method Combines INRs and GNNs for scalable graphon estimation.
result SIGL learns consistent graphons at arbitrary resolutions.
Proposes auditing for envy-freeness in recommender systems to assess individual preferences.
problem Auditing fairness in recommender systems for individual preferences.
method Formulates a pure exploration problem in multi-armed bandits, proposing a sample-efficient algorithm with theoretical guarantees.
result Algorithm ensures fairness without deteriorating user experience on real-world datasets.
StarGAN model generates and recognizes emotions from facial expressions.
problem Emotion recognition and generation from facial expressions.
method Used StarGAN model to train on a new emotion dataset of 4K videos.
result Trained StarGAN model can generate and recognize emotions based on valence arousal scores.
GARIM theory explains how conscious manipulation of internal representations enhances goal-directed behavior.
problem Limited understanding of how consciousness supports flexible goal-directed cognition.
method Extending a three-component theory of flexible cognition, proposing GARIM theory.
result Conscious states actively manipulate internal representations to align with goals, enhancing flexibility.
Two-stream model recognizes affect from audio and video.
problem Human affect recognition in real-world settings.
method Two-stream aural-visual analysis model with separate audio and visual processing.
result Model achieves promising results on Aff-Wild2 database.
GRAM addresses healthcare data insufficiency and interpretation challenges using graph-based attention.
problem Data insufficiency and lack of interpretability in healthcare predictive modeling.
method GRAM integrates EHR with medical ontologies, using attention mechanisms to represent medical concepts.
result GRAM outperforms RNN in accuracy and interpretability, using less data.
Optimizes master faces for 2D and 3D face verification using evolutionary algorithms and neural networks.
problem Impersonation attacks using master faces for face-based identity authentication.
method Evolutionary algorithm in latent space of StyleGAN, neural network to direct search, 2D and 3D face reconstruction.
result Obtains high impersonation rates with fewer master faces for 2D and 3D face verification.
Collectives can manipulate learning platforms by coordinated data submission, requiring strategic assessments and algorithms.
problem Collectives can influence learning platforms by altering data, posing risks and requiring strategic planning.
method Developed a theoretical and algorithmic framework to understand and mitigate collective manipulation of learning platforms.
result Demonstrated the need for strategic assessments and implementable coordination algorithms to prevent collective manipulation.
Face recognition systems are vulnerable to composite face reconstruction attacks.
problem Vulnerability of face recognition systems to composite face reconstruction attacks.
method Assumed attacker uses composite face parts to reconstruct faces faster and more efficiently.
result Current face recognition systems are extremely vulnerable to random search attacks.
SpecRaGE learns robust multi-view representations using graph Laplacians and neural networks.
problem Challenges in generalizing and scaling multi-view representation learning methods.
method SpecRaGE integrates graph Laplacian methods with neural networks to learn robust representations.
result SpecRaGE outperforms state-of-the-art methods in noisy and contaminated data scenarios.
This paper surveys scalable automated alignment methods for LLMs.
problem Scalability issues in traditional human-annotated alignment methods for LLMs.
method Categorizes and discusses various automated alignment methods.
result Emerging automated alignment methods are effective and scalable.
Inference-aware meta-alignment of LLMs reduces computational cost.
problem Aligning LLMs to diverse human preferences is challenging due to conflicting criteria.
method IAMA trains a base model to be aligned to multiple tasks via different inference-time alignment algorithms, using non-linear GRPO for optimization.
result IAMA enables effective alignment of LLMs to multiple criteria with limited computational budget.
Conformal Alignment ensures trustworthy outputs from foundation models.
problem Ensuring outputs from foundation models align with human values in high-stakes tasks.
method A framework that trains an alignment predictor using reference data to select trustworthy outputs.
result Conformal Alignment accurately identifies trustworthy outputs via lightweight training over moderate reference data.
Study evaluates manifold alignment methods for noisy double pendulum dynamics.
problem Aligning manifolds of double pendulum dynamics under noise.
method Compared four manifold alignment methods: semi-supervised feature-level global and local.
result Local alignment methods were more robust to noise and faster.
LPL optimizes embeddings to align local neighborhoods, improving cross-lingual word alignment.
problem Aligning embeddings across different datasets and languages.
method Locality Preserving Loss (LPL) optimizes model to project embeddings while maintaining local neighborhoods and aligning them.
result LPL-based alignment leads to better and consistent accuracy, especially in small training set settings.
Extends reinforcement learning alignment to scalar rewards, improving math reasoning.
problem Designing reinforcement learning algorithms for general LLM alignment.
method Introduces f-GRPO and f-HAL, estimating f-divergences between reward-aligned and unaligned distributions.
result Improves math reasoning RLVR tasks and mitigates reward hacking.
The paper proposes a learning-theoretic perspective on representation alignment.
problem Understanding how AI models' representations become aligned as they scale.
method Reviewing and connecting different notions of alignment, focusing on stitching.
result Relating properties of stitching to kernel alignment of representations.
DKN uses knowledge graphs to improve news recommendation.
problem Limited personalized news recommendations due to lack of external knowledge.
method Integrates knowledge graph representation into news recommendation using a deep knowledge-aware network (DKN).
result DKN achieves substantial gains over state-of-the-art models in click-through rate prediction.
Unified model for age-invariant face recognition with photorealistic face synthesis.
problem Reliable face recognition across ages remains challenging due to significant intra-class variations.
method Unified deep architecture for cross-age face synthesis and recognition, continuous face rejuvenation/aging, disentangled age-invariant face representations.
result Superior performance on CAFR and other cross-age datasets, promising generalizability to unconstrained face recognition.
This paper converts speech to match a face image and vice versa.
problem Matching speech to a face image and vice versa.
method Proposes a model with speech converter, face encoder/decoder, and voice encoder.
result Trained model converts speech to match a face image and generates a face image that matches the voice of input speech.
Universal adversarial patches prevent face detection in various frameworks.
problem Preventing face detection in state-of-the-art face detection systems.
method Investigated the phenomenon of patches that suppress face detection and proposed optimization-based approaches for automatic design.
result Universal adversarial patches can prevent face detection without introducing false positives.