TabOrder learns unsupervised causal variable orderings and enforces them with order-constrained attention for tabular prediction and imputation under distribution shifts.
super hub Canonical reference
Langley , title =
Canonical reference. 71% of citing Pith papers cite this work as background.
116
Pith papers citing it
Background
71% of classified citations
hub tools
citation-role summary
background 22
method 4
other 2
citation-polarity summary
claims ledger
- background tured diffusion bridge framework, SR involves learning a conditional stochastic coupling that transports mass from the low-resolution endpoint distribution to the high-resolution endpoint distribution, while preserving the conditioning signal provided by y. The same supervision protocol as described in Section 5.1 is employed, varying the paired fraction ρ∈[0,1] while maintaining a fixed total number of training samples. Appendix D contains detailed descrip- tions of data construction, model arc
- background The proof of (a) is straightforward under the assumption 2. proof of (b) E h eh(w)(n) 2 Fn i =mNE h Y (w) n+1 −y (w) n 2 Fn i .(9) Next, we add and subtract A(w)⊤ ∇f(x n) inside the norm and apply the inequality ∥u+v∥ 2 ≤ 2∥u∥2 + 2∥v∥2, which yields E h Y (w) n+1 −y (w) n 2 Fn i ≤2 A(w)⊤ ∇f(x n−τ (w) n )−y (w) n 2 + 2E h A(w)⊤e∇f(x n−τ (w) n )−A (w)⊤ ∇f(x n−τ (w) n ) 2 Fn i . (10) In view of Assumption 2 we obtain E h eh(w)(n) 2 Fn i ≤2mN A(w)⊤ ∇f(x n)−y (w) n 2 + 2mN ¯A2σ2, which establishes th
co-cited works
representative citing papers
Thermo-VL augments a frozen Molmo-7B VLM with a trainable thermal encoder and prompt-conditioned dual-attention fusion to improve cross-spectrum visual reasoning.
Seizure-Semiology-Suite provides a new clinically annotated video dataset and hierarchical benchmark that exposes weaknesses in current MLLMs for seizure semiology and demonstrates gains from fine-tuning and a neuro-symbolic classifier reaching 0.96 F1.
Tensor Cache augments sliding-window attention with an eviction-fed outer-product associative memory and a training correction to improve long-context performance under bounded memory.
JET is a conditional flow matching framework that generates EEG as continuous raw sequences with added constraints for spectral and temporal properties, achieving over 40% lower TS-FID than prior discrete denoising methods on three benchmarks.
UOTIP learns an unbalanced optimal transport map from noisy to clean distributions for unpaired inverse problems, incorporating a likelihood cost and proving existence/uniqueness via quadratic cost satisfying the twist condition.
PG-DPO is a new variational framework that replaces Bellman recursion with a Pontryagin-guided adjoint-MC projection for RL under non-exponential discounting and shows gains on hyperbolic and survival benchmarks.
JanusPipe introduces SymFold and WaveK to enable efficient 3D-parallel training for conservative MLIPs, reporting 1.51x and 1.45x average throughput gains over 1F1B and Hanayo baselines on 32 GPUs.
SymTrack is the first systematic detection-free framework for scene text tracking that constructs benchmarks from video text spotting datasets and reports up to 11.97% AUC gains over prior trackers.
Lang2MLIP is an LLM multi-agent framework that automates end-to-end development of machine learning interatomic potentials from natural language input for heterogeneous materials systems.
The authors derive a Maximally Scale-Stable Parameterization (MSSP) for MoE models that achieves robust learning-rate transfer and monotonic performance gains with scale across co-scaling regimes of width, experts, and sparsity.
BOOKMARKS introduces searchable bookmarks as reusable answers to storyline questions, enabling active initialization and passive synchronization for more consistent role-playing agent memory than recurrent summarization.
CAWI replaces standard random initialization of input-to-hidden weights in randomized neural networks with samples drawn from a data-fitted copula that preserves observed feature dependencies, yielding consistent accuracy gains on 83 classification benchmarks.
Probability-of-Hit acquisition function ranks perturbation candidates by posterior probability of threshold exceedance, with asymptotic optimality proof and up to 6.4% gains on real immunology data.
LE-SAM inverts SAM by fixing the loss budget instead of the parameter-space radius, yielding better generalization across benchmarks.
AIDA is the first end-to-end autonomous agent that combines a domain-specific language with Pareto-guided reinforcement learning to discover insights from complex business data.
ABGD parametrizes piecewise linear functions as difference of max-affine functions and converges linearly to an epsilon-accurate solution with O(d max(sigma/epsilon,1)^2) samples under sub-Gaussian noise, which is minimax optimal up to logs.
PODiff performs conditional diffusion in a fixed, variance-ordered POD latent space to enable efficient probabilistic super-resolution of high-dimensional scientific fields with lower memory and better-calibrated uncertainty than pixel-space or dropout baselines.
MPFM models flow matching velocity as a Gaussian mixture prior per normal class plus a mutual information regularizer to improve open-set anomaly detection over unimodal prototypes.
In multi-label neural collapse, terminal geometry is controlled by the centered label covariance spectrum κ_m derived from label distribution moments, with higher-multiplicity prototypes following class-frequency-weighted synthesis instead of uniform averaging.
mPL measures attacker-aligned privacy leakage from joint data releases and AmPL provides an adaptive way to bound it with low utility cost in ML settings.
NonZero introduces an interaction score and bandit-formalized proposal rule for local agent deviations in multi-agent MCTS, delivering a sublinear local-regret guarantee and improved sample efficiency on game benchmarks without full joint-action enumeration.
A new first-order algorithm for multi-task learning with shared linear representation achieves near-optimal error rates in constant iterations, improving existing methods by a factor of k.
ResRL decouples shared semantics between positive and negative responses in LLM reinforcement learning via SVD-based projection residuals, outperforming baselines including NSR by up to 9.4% on math reasoning benchmarks.
citing papers explorer
-
Learning Causal Orderings for In-Context Tabular Prediction
TabOrder learns unsupervised causal variable orderings and enforces them with order-constrained attention for tabular prediction and imputation under distribution shifts.
-
Thermo-VL: Extending Vision-Language Models to Thermal Infrared Perception
Thermo-VL augments a frozen Molmo-7B VLM with a trainable thermal encoder and prompt-conditioned dual-attention fusion to improve cross-spectrum visual reasoning.
-
Seizure-Semiology-Suite (S3): A Clinically Multimodal Dataset, Benchmark, and Models for Seizure Semiology Understanding
Seizure-Semiology-Suite provides a new clinically annotated video dataset and hierarchical benchmark that exposes weaknesses in current MLLMs for seizure semiology and demonstrates gains from fine-tuning and a neuro-symbolic classifier reaching 0.96 F1.
-
Tensor Cache: Eviction-conditioned Associative Memory for Transformers
Tensor Cache augments sliding-window attention with an eviction-fed outer-product associative memory and a training correction to improve long-context performance under bounded memory.
-
Let EEG Models Learn EEG
JET is a conditional flow matching framework that generates EEG as continuous raw sequences with added constraints for spectral and temporal properties, achieving over 40% lower TS-FID than prior discrete denoising methods on three benchmarks.
-
UOTIP: Unbalanced Optimal Transport Map for Unpaired Inverse Problems
UOTIP learns an unbalanced optimal transport map from noisy to clean distributions for unpaired inverse problems, incorporating a likelihood cost and proving existence/uniqueness via quadratic cost satisfying the twist condition.
-
Beyond the Bellman Recursion: A Pontryagin-Guided Framework for Non-Exponential Discounting
PG-DPO is a new variational framework that replaces Bellman recursion with a Pontryagin-guided adjoint-MC projection for RL under non-exponential discounting and shows gains on hyperbolic and survival benchmarks.
-
JanusPipe: Efficient Pipeline Parallel Training for Machine Learning Interatomic Potentials
JanusPipe introduces SymFold and WaveK to enable efficient 3D-parallel training for conservative MLIPs, reporting 1.51x and 1.45x average throughput gains over 1F1B and Hanayo baselines on 32 GPUs.
-
Beyond Detection: A Structure-Aware Framework for Scene Text Tracking
SymTrack is the first systematic detection-free framework for scene text tracking that constructs benchmarks from video text spotting datasets and reports up to 11.97% AUC gains over prior trackers.
-
Lang2MLIP: End-to-End Language-to-Machine Learning Interatomic Potential Development with Autonomous Agentic Workflows
Lang2MLIP is an LLM multi-agent framework that automates end-to-end development of machine learning interatomic potentials from natural language input for heterogeneous materials systems.
-
How to Scale Mixture-of-Experts: From muP to the Maximally Scale-Stable Parameterization
The authors derive a Maximally Scale-Stable Parameterization (MSSP) for MoE models that achieves robust learning-rate transfer and monotonic performance gains with scale across co-scaling regimes of width, experts, and sparsity.
-
BOOKMARKS: Efficient Active Storyline Memory for Role-playing
BOOKMARKS introduces searchable bookmarks as reusable answers to storyline questions, enabling active initialization and passive synchronization for more consistent role-playing agent memory than recurrent summarization.
-
CAWI: Copula-Aligned Weight Initialization for Randomized Neural Networks
CAWI replaces standard random initialization of input-to-hidden weights in randomized neural networks with samples drawn from a data-fitted copula that preserves observed feature dependencies, yielding consistent accuracy gains on 83 classification benchmarks.
-
Many Needles in a Haystack: Active Hit Discovery for Perturbation Experiments
Probability-of-Hit acquisition function ranks perturbation candidates by posterior probability of threshold exceedance, with asymptotic optimality proof and up to 6.4% gains on real immunology data.
-
Fix the Loss, Not the Radius: Rethinking the Adversarial Perturbation of Sharpness-Aware Minimization
LE-SAM inverts SAM by fixing the loss budget instead of the parameter-space radius, yielding better generalization across benchmarks.
-
Towards Autonomous Business Intelligence via Data-to-Insight Discovery Agent
AIDA is the first end-to-end autonomous agent that combines a domain-specific language with Pareto-guided reinforcement learning to discover insights from complex business data.
-
Locally Near Optimal Piecewise Linear Regression in High Dimensions via Difference of Max-Affine Functions
ABGD parametrizes piecewise linear functions as difference of max-affine functions and converges linearly to an epsilon-accurate solution with O(d max(sigma/epsilon,1)^2) samples under sub-Gaussian noise, which is minimax optimal up to logs.
-
PODiff: Latent Diffusion in Proper Orthogonal Decomposition Space for Scientific Super-Resolution
PODiff performs conditional diffusion in a fixed, variance-ordered POD latent space to enable efficient probabilistic super-resolution of high-dimensional scientific fields with lower memory and better-calibrated uncertainty than pixel-space or dropout baselines.
-
Mixture Prototype Flow Matching for Open-Set Supervised Anomaly Detection
MPFM models flow matching velocity as a Gaussian mixture prior per normal class plus a mutual information regularizer to improve open-set anomaly detection over unimodal prototypes.
-
How Label Imbalance Shapes Geometry: A General Spectral Analysis of Multi-Label Neural Collapse
In multi-label neural collapse, terminal geometry is controlled by the centered label covariance spectrum κ_m derived from label distribution moments, with higher-multiplicity prototypes following class-frequency-weighted synthesis instead of uniform averaging.
-
Metric-Normalized Posterior Leakage (mPL): Attacker-Aligned Privacy for Joint Consumption
mPL measures attacker-aligned privacy leakage from joint data releases and AmPL provides an adaptive way to bound it with low utility cost in ML settings.
-
NonZero: Interaction-Guided Exploration for Multi-Agent Monte Carlo Tree Search
NonZero introduces an interaction score and bandit-formalized proposal rule for local agent deviations in multi-agent MCTS, delivering a sublinear local-regret guarantee and improved sample efficiency on game benchmarks without full joint-action enumeration.
-
Near-optimal and Efficient First-Order Algorithm for Multi-Task Learning with Shared Linear Representation
A new first-order algorithm for multi-task learning with shared linear representation achieves near-optimal error rates in constant iterations, improving existing methods by a factor of k.
-
ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning
ResRL decouples shared semantics between positive and negative responses in LLM reinforcement learning via SVD-based projection residuals, outperforming baselines including NSR by up to 9.4% on math reasoning benchmarks.
-
Watch Your Step: Information Injection in Diffusion Models via Shadow Timestep Embedding
Timestep embeddings in diffusion models function as a separable side channel that can carry dedicated information for adversarial injection or detection.
-
Privatar: Scalable Privacy-preserving Multi-user VR via Secure Offloading
Privatar uses horizontal frequency partitioning and distribution-aware minimal perturbation to enable private offloading of VR avatar reconstruction, supporting 2.37x more users with modest overhead.
-
Validity-Calibrated Reasoning Distillation
Validity-calibrated reasoning distillation improves transfer of reasoning skills by modulating updates based on relative local validity of next steps instead of enforcing full trajectory imitation.
-
Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
o1-like models overthink easy tasks; self-training reduces compute use without accuracy loss on GSM8K, MATH500, GPQA, and AIME.
-
RouterBench: A Benchmark for Multi-LLM Routing System
RouterBench supplies a standardized benchmark, 405k+ inference dataset, theoretical framework, and comparative analysis for multi-LLM routing systems.
-
Fast Inference from Transformers via Speculative Decoding
Speculative decoding accelerates exact sampling from large autoregressive models by 2-3x on T5-XXL by running smaller approximation models in parallel to propose token sequences that the large model then verifies in batches while preserving the original output distribution.
-
Fast Transformer Decoding: One Write-Head is All You Need
Multi-query attention shares keys and values across heads in Transformers, greatly reducing memory bandwidth for faster decoding with only minor quality loss.
-
PGT: Procedurally Generated Tasks for improving visual grounding in MLLMs
PGT generates synthetic tasks via geometric overlays on images to supply dense visual supervision, improving spatial and relational understanding in MLLMs by up to 20% on targeted benchmarks.
-
Convex Optimization for Alignment and Preference Learning on a Single GPU
COALA applies convex optimization reformulations of neural networks to direct preference optimization, claiming single-GPU training with ~18% of DPO's TFLOPs and competitive performance on multiple datasets and models up to 8B parameters.
-
Implicit Safety Alignment from Crowd Preferences
A hierarchical framework extracts implicit safety criteria from crowd preferences and composes them via high-level policy to reduce safety violations in downstream RL tasks without explicit safety rewards.
-
Towards Context-Invariant Safety Alignment for Large Language Models
Introduces AIR, an asymmetric regularization that anchors open-ended safety prompts to verifiable ones via stop-gradient, improving invariance and accuracy when combined with group preference optimization.
-
Convergence of Consensus-Based Particle Methods for Nonconvex Bi-Level Optimization
Establishes exponential convergence in Wasserstein distance for the mean-field limit and finite-particle approximation of a consensus-based method solving nonconvex bi-level optimization problems.
-
SAGE: Shaping Anchors for Guided Exploration in RLVR of LLMs
SAGE reshapes the reverse-KL anchor via guide function q(x,y) for controllable empirical support expansion, yielding gains in both pass@1 and pass@k on math reasoning benchmarks.
-
Polar probe linearly decodes semantic structures from LLMs
LLMs represent semantic relations geometrically via embedding distance and direction; a linear Polar Probe decodes these structures from middle-layer activations and generalizes to new entities.
-
Frequency Bias and OOD Generalization in Neural Operators under a Variable-Coefficient Wave Equation
FNO exhibits strong frequency bias with sharp OOD error growth on high-frequency inputs in wave equations, while DeepONet shows milder degradation despite higher baseline error.
-
CTFusion: A CTF-based Benchmark for LLM Agent Evaluation
CTFusion is a live-CTF streaming benchmark that prevents data contamination by forwarding only the first correct flag per challenge under a shared team account.
-
ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox
ComplexMCP benchmark shows top LLM agents achieve under 60% success on dynamic interdependent tool tasks versus 90% for humans, due to tool retrieval saturation, over-confidence, and strategic defeatism.
-
The general regularisation scheme applied to conditional density estimation
The general regularization scheme is extended to conditional density estimation, yielding a new estimator with proven convergence rates that matches or beats the Nadaraya-Watson estimator in experiments.
-
Modeling Implicit Conflict Monitoring Mechanisms against Stereotypes in LLMs
LLMs contain identifiable COCO neurons that enable implicit self-correction against stereotypes; targeted editing of these neurons improves fairness and robustness to jailbreaks while preserving generation quality.
-
QueST: Persistent Queries as Semantic Monitors for Drift Suppression in Long-Horizon Tracking
QueST replaces local point tracking with persistent semantic queries that globally attend to spatio-temporal features and apply 3D grounding to suppress drift, cutting absolute point error by 67.7% versus TAP-Net on long articulated sequences.
-
From Passive Reuse to Active Reasoning: Grounding Large Language Models for Neuro-Symbolic Experience Replay
NSER uses zero-shot LLMs to induce behavioral rules from RL trajectories, grounds them in differentiable first-order logic, and applies the symbolic structures to dynamically reweight experience replay for better sample efficiency.
-
Adversary-Robust Learning from Fully Asynchronous Directional Derivative Estimates
FAR-SIGN achieves adversary-resilient fully asynchronous optimization via signed directional projections and two-timescale correction, with almost-sure convergence to stationary points at rates O(n^{-1/4+ε}) first-order and O(n^{-1/6+ε}) zeroth-order.
-
Kinematics-Driven Gaussian Shape Deformation for Blurry Monocular Dynamic Scenes
Kinematics-GS reparameterizes Gaussian shapes along motion trajectories with a kinematic prior to reconstruct dynamic 3D scenes from blurry monocular videos by separating dynamic and static components and using coarse-to-fine optimization.
-
MARLaaS: Multi-Tenant Asynchronous Reinforcement Learning as a Service
MARLaaS enables concurrent RL fine-tuning across up to 32 tasks using LoRA adapters and a disaggregated asynchronous architecture, matching single-task performance while improving accelerator utilization by 4.3x and cutting end-to-end time by 85%.
-
Where's the Plan? Locating Latent Planning in Language Models with Lightweight Mechanistic Interventions
Future-rhyme information is linearly decodable at line boundaries across model families and strengthens with scale, yet only Gemma-3-27B causally depends on it, with the driver migrating to the boundary around layer 30 and localizing to five attention heads.
-
Accelerating Langevin Monte Carlo via Efficient Stochastic Runge--Kutta Methods beyond Log-Concavity
A Hessian-free stochastic Runge-Kutta LMC algorithm achieves strong order 1.5 with two gradient evaluations per step and uniform-in-time convergence O(d^{3/2} h^{3/2}) in non-log-concave settings.