Quotient-space diffusion models generate correct symmetric distributions by removing redundancy on the quotient space, simplifying learning and improving results on small molecules and proteins under SE(3) symmetry.
super hub Canonical reference
Advances in neural information processing systems , volume=
Canonical reference. 86% of citing Pith papers cite this work as background.
143
Pith papers citing it
Background
86% of classified citations
hub tools
citation-role summary
background 6
method 1
citation-polarity summary
authors
co-cited works
representative citing papers
Regularized Muon induces a damped Hamiltonian flow on probability measures over matrix parameters, yielding exponential convergence under gradient dominance assumptions.
TabOrder learns unsupervised causal variable orderings and enforces them with order-constrained attention for tabular prediction and imputation under distribution shifts.
ConTact decomposes CDR design into surface fingerprint learning, contact prediction, and contact-gated sequence generation using distance-biased attention and weighted loss, reporting 7% RMSD and 10% F1 gains on CHIMERA-Bench.
BrepForge factorizes B-rep synthesis into face-aware autoregressive wireframe composition followed by boundary-conditioned surface instantiation using learning-free geometric priors.
Object functionalization is cast as neural graph completion over a functional graph of parts, contacts, and motions, followed by geometry realization that also rectifies erroneous motions, demonstrated on furniture with a new paired dataset.
New metrics KSS and KPS are introduced to evaluate multilingual machine unlearning quality and cross-language consistency in LLMs, addressing limitations of single-language evaluation protocols.
A diameter criterion tied to a potential function certifies convergence of difference inclusions, enabling discrete proofs for first-order optimization methods with diminishing steps.
ViT-K uses Vision Transformers and Koopman operators to learn stable long-term spatiotemporal dynamics of coupled fluid-porous media flows from sparse data.
OpenSGA fuses vision-language, textual, and geometric features via a distance-gated attention encoder and minimum-cost-flow allocator to outperform prior methods on both frame-to-scan and subscan-to-subscan 3D scene graph alignment, backed by a new 700k-sample ScanNet-SG dataset.
Self-attention acts as a covariance readout that unifies in-context learning via population gradient descent and repetitive generation via asymptotic Markov behavior.
Temporal correlations from lazy random walks enable efficient SGD learning of k-juntas via temporal-difference loss on ReLU networks, achieving linear sample complexity in d.
Polyphonia improves zero-shot stem-specific timbre transfer in polyphonic music by 15.5% target alignment via acoustic-informed attention calibration that uses probabilistic priors to set coarse boundaries.
ALiBi bias is the expectation of positional LSH-induced block masks, yielding spectral and max-norm approximation bounds that reduce long-context biased attention to randomized short-context unbiased attention.
CaTR applies value-decomposed RL with hierarchical conflict-aware observations to achieve better safety-efficiency trade-offs than planning, optimization, and standard RL baselines in a realistic airport taxiway simulation.
The Sinkhorn treatment effect is a new entropic optimal transport measure of divergence between counterfactual distributions that admits first- and second-order pathwise differentiability, debiased estimators, and asymptotically valid tests for distributional treatment effects.
LG-CoTrain, an LLM-guided co-training method, outperforms classical semi-supervised baselines for crisis tweet classification in low-resource settings with 5-25 labeled examples per class.
EyeCue detects driver cognitive distraction by modeling gaze-visual context interactions in egocentric videos and achieves 74.38% accuracy on the new CogDrive dataset, outperforming 11 baselines.
LC-MAPF uses multi-round local communication between neighboring agents in a pre-trained model to outperform prior learning-based MAPF solvers on diverse unseen scenarios while preserving scalability.
Structured per-agent randomness via ranked masking in attention allows symmetric agents to break ties and coordinate, achieving perfect success on symmetric tasks where deterministic policies fail and enabling zero-shot transfer across team sizes.
Synthetic data augmentation helps channel-mixing time series models but degrades channel-independent ones, with reliable gains only from seasonal-trend generators and gradual schedules in low-resource settings.
SATFormer uses a context-dependent gate for selective reuse of early Transformer representations, improving validation loss and zero-shot accuracy especially on retrieval benchmarks.
OGPP is a particle flow-matching method using orbit-space canonicalization and geometric paths that achieves lower error and fewer steps than prior approaches on 3D benchmarks.
VAnim creates open-domain text-to-SVG animations via sparse state updates on a persistent DOM tree, identification-first planning, and rendering-aware RL with a new 134k-example benchmark.
citing papers explorer
-
PULSE: Generative Phase Evolution for Non-Stationary Time Series Forecasting
PULSE is a physics-informed plug-and-play framework that uses phase-anchored disentanglement, a Phase Router, and statistic-aware mixup to mitigate Phase Amnesia in non-stationary forecasting and achieve strong results with simple backbones.
-
Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making
Ada-Diffuser is a causal diffusion model that jointly learns observed interaction structure and underlying latent dynamics from minimal observations for adaptive planning and policy learning.
-
AdaEraser: Training-Free Object Removal via Adaptive Attention Suppression
AdaEraser introduces token-wise adaptive attention suppression in diffusion denoising to enable high-quality training-free object removal by modulating suppression according to evolving self-attention maps.
-
AnyAct: Towards Human Reenactment of Character Motion From Video
AnyAct generates editable human reenactments from character videos via conditional motion generation from transferable sparse local 2D articulated cues, with designs for human-only supervision and global-local decoupling.
-
TOPOS: High-Fidelity and Efficient Industry-Grade 3D Head Generation
TOPOS creates high-fidelity 3D heads with fixed industry topology from single images via a specialized VAE with Perceiver Resampler and a rectified flow transformer.
-
Set-Aggregated Genome Embeddings for Microbiome Abundance Prediction
Set-aggregated genome embeddings from genomic language models predict microbiome abundance profiles with improved generalization to novel genomes over classical bioinformatics methods.
-
Training-Inference Consistent Segmented Execution for Long-Context LLMs
A training-inference consistent segmented execution framework for long-context LLMs matches full-context performance with substantially lower peak memory at very long lengths.
-
WorldComp2D: Spatio-semantic Representations of Object Identity and Location from Local Views
WorldComp2D explicitly structures latent space geometry by object identity and spatial proximity via a proximity-dependent encoder and localizer, cutting parameters up to 4X and FLOPs 2.2X versus state-of-the-art lightweight models on facial landmark localization while staying real-time on CPU.
-
Towards Understanding Continual Factual Knowledge Acquisition of Language Models: From Theory to Algorithm
Theoretical analysis of continual factual knowledge acquisition shows data replay stabilizes pretrained knowledge by shifting convergence dynamics while regularization only slows forgetting, leading to the STOC method for attention-based replay selection.
-
The two clocks and the innovation window: When and how generative models learn rules
Generative models learn rules before memorizing data, creating an innovation window whose width depends on dataset size and rule complexity, observed in both diffusion and autoregressive architectures.
-
HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution
HAGE proposes a trainable weighted graph memory framework with LLM intent classification, dynamic edge modulation, and RL optimization that improves long-horizon reasoning accuracy in agentic LLMs over static baselines.
-
Continuity Laws for Sequential Models
S4 models exhibit stable time-continuity unlike sensitive S6 models, with task continuity predicting performance and enabling temporal subsampling for better efficiency.
-
CarCrashNet: A Large-Scale Dataset and Hierarchical Neural Solver for Data-Driven Structural Crash Simulation
CarCrashNet supplies a large multi-modal crash simulation benchmark and CrashSolver neural model for data-driven full-vehicle crash prediction, validated against experiments and commercial solvers.
-
PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts
PragLocker generates function-preserving but non-portable prompts for LLM agents via code-symbol semantic anchoring followed by target-model feedback noise injection.
-
Temporal Smoothness Doubly Robust Learning for Debiased Knowledge Tracing
TSDR applies doubly robust learning with temporal smoothness regularization to deliver unbiased and low-variance knowledge tracing estimates from selectively observed student data.
-
Large Vision-Language Models Get Lost in Attention
In LVLMs, attention can be replaced by random Gaussian weights with little or no performance loss, indicating that current models get lost in attention rather than efficiently using visual context.
-
Scaling Pretrained Representations Enables Label-Free Out-of-Distribution Detection Without Fine-Tuning
Scaling pretrained representations improves label-free OOD detection on frozen backbones, causing performance gaps between global and local detectors to vanish across vision and language tasks.
-
A Novel Graph-Regulated Disentangling Mamba Model with Sparse Tokens for Enhanced Tree Species Classification from MODIS Time Series
A graph-regulated disentangling Mamba model with sparse tokens achieves 93.94% accuracy classifying tree species from MODIS time series in Alberta and outperforms twelve prior models.
-
ZAYA1-8B Technical Report
ZAYA1-8B is a reasoning MoE model with 700M active parameters that matches larger models on math and coding benchmarks and reaches 91.9% on AIME'25 via Markovian RSA test-time compute.
-
On the (In-)Security of the Shuffling Defense in the Transformer Secure Inference
An attack aligns differently shuffled intermediate activations from secure Transformer inference queries to recover model weights with low error using roughly one dollar of queries.
-
CAST: Mitigating Object Hallucination in Large Vision-Language Models via Caption-Guided Visual Attention Steering
CAST reduces object hallucination in LVLMs by 6.03% on average across five models and five benchmarks by identifying caption-sensitive attention heads and applying optimized steering directions to their outputs, with negligible added inference cost.
-
A Queueing-Theoretic Framework for Stability Analysis of LLM Inference with KV Cache Memory Constraints
A queueing model derives stability conditions for LLM inference services under combined compute and KV cache memory limits, with experimental validation showing typical deviations under 10%.
-
High-Fidelity Single-Image Head Modeling with Industry-Grade Topology
A single-image head reconstruction method uses coarse-to-fine optimization with normal consistency, landmarks, and geometry-aware constraints on curvature and conformality to produce meshes with industry-grade topology and preserved facial identity.
-
QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL
QHyer replaces return-to-go with a state-conditioned Q-estimator and adds a gated hybrid attention-mamba backbone to achieve state-of-the-art performance in offline goal-conditioned RL on both Markovian and non-Markovian datasets.
-
Verbal-R3: Verbal Reranker as the Missing Bridge between Retrieval and Reasoning
Verbal-R3 uses a verbal reranker to generate analytic narratives that guide retrieval and reasoning in LLMs, achieving SOTA results on complex QA benchmarks.
-
Deep Kernel Learning for Stratifying Glaucoma Trajectories
A deep kernel learning architecture with transformer feature extraction on clinical-BERT embeddings and Gaussian process backend identifies three glaucoma subgroups by decoupling progression trajectories from current visual acuity in multimodal EHR data.
-
AGoQ: Activation and Gradient Quantization for Memory-Efficient Distributed Training of LLMs
AGoQ delivers up to 52% lower memory use and 1.34x faster training for 8B-32B LLaMA models by using near-4-bit adaptive activations and 8-bit gradients while preserving pretraining convergence and downstream accuracy.
-
Parameter-Efficient Adaptation of Pre-Trained Vision Foundation Models for Active and Passive Seismic Data Denoising
Adapting vision foundation models with LoRA and kurtosis-guided unsupervised test-time adaptation matches or exceeds domain-specific models for seismic denoising across multiple sites and unseen data.
-
Temporal Taskification in Streaming Continual Learning: A Source of Evaluation Instability
Different valid temporal partitions of the same streaming dataset can produce materially different rankings and performance numbers for continual learning methods.
-
Finding Meaning in Embeddings: Concept Separation Curves
Concept Separation Curves provide a classifier-independent method to visualize and quantify how sentence embeddings distinguish conceptual meaning from syntactic variations across languages and domains.
-
ReaGeo: Reasoning-Enhanced End-to-End Geocoding with LLMs
ReaGeo is an end-to-end LLM framework for geocoding that uses geohash text generation, Chain-of-Thought spatial reasoning, and distance-based RL to accurately predict points and regions from explicit and vague queries.
-
Mol-Debate: Multi-Agent Debate Improves Structural Reasoning in Molecular Design
Mol-Debate applies multi-agent debate in an iterative loop with perspective orchestration to achieve state-of-the-art text-guided molecular design, scoring 59.82% exact match on ChEBI-20 and 50.52% weighted success on S2-Bench.
-
Hybrid Policy Distillation for LLMs
Hybrid Policy Distillation unifies existing knowledge distillation methods for LLMs into a reweighted log-likelihood objective and introduces a hybrid forward-reverse KL approach with mixed data sampling to improve stability, efficiency, and performance.
-
Bangla Key2Text: Text Generation from Keywords for a Low Resource Language
Bangla Key2Text releases 2.6M keyword-text pairs and demonstrates that fine-tuned mT5 and BanglaT5 outperform zero-shot LLMs on keyword-conditioned Bangla text generation.
-
Deep Supervised Contrastive Learning of Pitch Contours for Robust Pitch Accent Classification in Seoul Korean
Dual-Glob applies supervised contrastive learning to classify fine-grained pitch accent patterns from F0 contours in Seoul Korean, achieving 77.75% accuracy and 51.54% F1 on a new dataset of 10,093 manually annotated accentual phrases.
-
SAMoRA: Semantic-Aware Mixture of LoRA Experts for Task-Adaptive Learning
SAMoRA is a parameter-efficient fine-tuning framework that uses semantic-aware routing and task-adaptive scaling within a Mixture of LoRA Experts to improve multi-task performance and generalization over prior methods.
-
AlignCultura: Towards Culturally Aligned Large Language Models?
Align-Cultura introduces the CULTURAX dataset and shows that culturally fine-tuned LLMs improve joint HHH scores by 4-6%, cut cultural failures by 18%, and gain 10-12% efficiency with minimal leakage.
-
mHC: Manifold-Constrained Hyper-Connections
mHC projects hyper-connection residual spaces onto a manifold to restore identity mapping, enabling stable large-scale training with performance gains over standard HC.
-
ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution
ShinkaEvolve improves sample efficiency in LLM-driven program evolution via parent sampling, code novelty rejection-sampling, and bandit LLM ensemble selection, achieving new SOTA circle packing with 150 samples and gains on math reasoning and competitive programming tasks.
-
Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning
Math reasoning gains in LLMs rarely transfer to general domains; RL tuning generalizes while SFT causes forgetting and representation drift.
-
Towards an AI co-scientist
A multi-agent AI system generates novel biomedical hypotheses that show promising experimental validation in drug repurposing for leukemia, new targets for liver fibrosis, and a bacterial gene transfer mechanism.
-
CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer
CogVideoX generates coherent 10-second text-to-video outputs at high resolution using a 3D VAE, expert adaptive LayerNorm transformer, progressive training, and a custom data pipeline, claiming state-of-the-art results.
-
NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models
NV-Embed achieves first place on the MTEB leaderboard across 56 tasks by combining a latent attention layer, causal-mask removal, two-stage contrastive training, and data curation for LLM-based embedding models.
-
Capabilities of Gemini Models in Medicine
Med-Gemini sets new records on 10 of 14 medical benchmarks including 91.1% on MedQA-USMLE, beats GPT-4V by 44.5% on multimodal tasks, and surpasses humans on medical text summarization.
-
TD-MPC2: Scalable, Robust World Models for Continuous Control
TD-MPC2 scales an implicit world-model RL method to a 317M-parameter agent that masters 80 tasks across four domains with a single hyperparameter configuration.
-
Multi-Beholder: Biomarker Prediction for Low-Grade Glioma with Multiple Instance Learning and One-Class Classification
Multi-Beholder integrates one-class classification into multiple instance learning to predict LGG biomarker status from histopathology images, reporting AUCs of 0.973 on TCGA-LGG and 0.820 on an external Xiangya cohort.
-
LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment
LanguageBind aligns video, infrared, depth, and audio to a frozen language encoder via contrastive learning on the new VIDAL-10M dataset, extending video-language pretraining to N modalities.
-
Reasoning with Language Model is Planning with World Model
RAP turns LLMs into dual world-model and planning agents via MCTS to generate better reasoning paths, outperforming CoT baselines and achieving 33% relative gains over GPT-4 CoT using LLaMA-33B on plan generation.
-
Towards Expert-Level Medical Question Answering with Large Language Models
Med-PaLM 2 achieves 86.5% accuracy on MedQA and approaches or exceeds prior state-of-the-art on other medical QA benchmarks while receiving higher physician preference ratings than human answers on consumer questions.
-
ART: Automatic multi-step reasoning and tool-use for large language models
ART automatically generates multi-step reasoning programs with tool integration for LLMs, yielding substantial gains over few-shot and auto-CoT prompting on BigBench and MMLU while matching hand-crafted CoT on most tasks.