Introduces Repeated Descent framework achieving 1/046-competitive posted-price mechanism for online budget-feasible auctions with submodular valuations under secretary arrivals, plus constant-competitive for non-monotone and an Omega(log n / (log log n)^2) lower bound for XOS.
hub
(new) Finding minimum congestion spanning trees
32 Pith papers cite this work. Polarity classification is still indexing.
32
Pith papers citing it
hub tools
years
2026 32representative citing papers
WikiVQABench is a human-curated collection of Wikipedia-based VQA items that require both visual evidence and external knowledge from Wikidata to answer correctly.
BrepForge factorizes B-rep synthesis into face-aware autoregressive wireframe composition followed by boundary-conditioned surface instantiation using learning-free geometric priors.
RISC reformulates self-consistency answer selection as a ranking task solved by a lightweight LambdaRank model with five hand-designed features, yielding better accuracy-efficiency trade-offs than majority voting on QA benchmarks.
DisImpact introduces a two-stage MLLM framework to classify disaster-related social media posts into ten impact categories and compute a unified physi-social impact index validated against FEMA and NASA ground-truth data.
A dataset-agnostic framework converts text tool-calling benchmarks to paired audio evaluations via TTS, speaker variation and noise, then evaluates seven omni-modal models showing model- and task-dependent performance with small text-to-voice gaps.
DeG models 3D Gaussians via learned octree density and uses VecSeq Sobol re-indexing to turn set generation into sequence modeling, claiming SOTA quality in single-image-to-3D.
UniVidX unifies diverse video generation tasks into one conditional diffusion model using stochastic condition masking, decoupled gated LoRAs, and cross-modal self-attention.
A training-free technique manipulates low-frequency noise in diffusion models to control image color and structure using low-frequency priors.
TTCD uses a non-stationary feature learner and reconstruction-guided distillation inside a transformer to infer contemporaneous and lagged causal graphs from non-stationary time series without strong noise assumptions.
A relaxed Picard iteration plus heteroscedastic boundary denoising lets Monte Carlo PDE solvers solve heat equations with nonlinear radiation boundary conditions more accurately than linearization.
Lightweight networks combine bracketed smartphone exposures as convex combinations of raw pixels to produce artifact-free HDR images that generalize from synthetic training to real captures.
ScaffoldAgent improves long-form report generation by modeling outline evolution as expansion, contraction, and revision guided by a utility function estimating downstream value.
DARS replaces single-shot response labels with distribution-aware supervision derived from input and output uncertainty to produce more reliable LLM routing policies.
AdMem introduces a unified bi-level memory framework with multi-agent automatic generation and reward-based long-term management that improves success on long-horizon LLM agent tasks.
PULSE stabilizes mmWave human pose estimation by screening Doppler motion prompts before injecting them into spatial magnitude reasoning.
TabEmb decouples LLM-based semantic column embeddings from graph-based structural modeling to produce joint representations that improve table annotation tasks.
QREAM rewrites documents to question-focused style using iterative ICL and distilled FT models, boosting RAG performance by up to 8% relative improvement.
CMSL uses a learnable module to disentangle user history into multiple pure sequences modeled with linear attention to improve recommendation performance over single-sequence approaches.
TRUST searches for minimal input changes that achieve a user-defined confidence target in PTM models, claiming perfect robustness and low cost on benchmarks versus standard boundary-crossing methods.
DD-GEPA decomposes and optimizes prompts with GEPA for LLM-based dialogue disentanglement, reporting accuracy gains over baseline and hand-crafted prompts on benchmarks.
The paper analyzes dependencies in genome alignment pipelines and implements synthesized optimizations from four prior tools into LASTZ to reduce serial bottlenecks.
CS students and recent grads prioritize pay and workplace culture over ethics in job searches and justify conflicting decisions with shared explanations such as money or lack of alternatives.
A tree-of-thoughts inspired hybrid extractive-abstractive LLM prompt yields better legal case judgment summaries than standard extractive or abstractive prompts.
citing papers explorer
-
Repeated Descent: A Framework for Online Budget-Feasible Auctions
Introduces Repeated Descent framework achieving 1/046-competitive posted-price mechanism for online budget-feasible auctions with submodular valuations under secretary arrivals, plus constant-competitive for non-monotone and an Omega(log n / (log log n)^2) lower bound for XOS.
-
WikiVQABench: A Knowledge-Grounded Visual Question Answering Benchmark from Wikipedia and Wikidata
WikiVQABench is a human-curated collection of Wikipedia-based VQA items that require both visual evidence and external knowledge from Wikidata to answer correctly.
-
BrepForge: Factorized B-rep Synthesis via Wireframe Composition and Boundary-Conditioned Surface Instantiation
BrepForge factorizes B-rep synthesis into face-aware autoregressive wireframe composition followed by boundary-conditioned surface instantiation using learning-free geometric priors.
-
Boosting Self-Consistency with Ranking
RISC reformulates self-consistency answer selection as a ranking task solved by a lightweight LambdaRank model with five hand-designed features, yielding better accuracy-efficiency trade-offs than majority voting on QA benchmarks.
-
DisImpact: Quantifying the Physi-Social Impact of Natural Disasters Through Social Media
DisImpact introduces a two-stage MLLM framework to classify disaster-related social media posts into ten impact categories and compute a unified physi-social impact index validated against FEMA and NASA ground-truth data.
-
From Text to Voice: A Reproducible and Verifiable Framework for Evaluating Tool Calling LLM Agents
A dataset-agnostic framework converts text tool-calling benchmarks to paired audio evaluations via TTS, speaker variation and noise, then evaluates seven omni-modal models showing model- and task-dependent performance with small text-to-voice gaps.
-
Generative 3D Gaussians with Learned Density Control
DeG models 3D Gaussians via learned octree density and uses VecSeq Sobol re-indexing to turn set generation into sequence modeling, claiming SOTA quality in single-image-to-3D.
-
UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors
UniVidX unifies diverse video generation tasks into one conditional diffusion model using stochastic condition masking, decoupled gated LoRAs, and cross-modal self-attention.
-
Colorful-Noise: Training-Free Low-Frequency Noise Manipulation for Color-Based Conditional Image Generation
A training-free technique manipulates low-frequency noise in diffusion models to control image color and structure using low-frequency priors.
-
TTCD:Transformer Integrated Temporal Causal Discovery from Non-Stationary Time Series Data
TTCD uses a non-stationary feature learner and reconstruction-guided distillation inside a transformer to infer contemporaneous and lagged causal graphs from non-stationary time series without strong noise assumptions.
-
Monte Carlo PDE Solvers for Nonlinear Radiative Boundary Conditions
A relaxed Picard iteration plus heteroscedastic boundary denoising lets Monte Carlo PDE solvers solve heat equations with nonlinear radiation boundary conditions more accurately than linearization.
-
Lucky High Dynamic Range Smartphone Imaging
Lightweight networks combine bracketed smartphone exposures as convex combinations of raw pixels to produce artifact-free HDR images that generalize from synthetic training to real captures.
-
ScaffoldAgent: Utility-Guided Dynamic Outline Optimization for Open-Ended Deep Research
ScaffoldAgent improves long-form report generation by modeling outline evolution as expansion, contraction, and revision guided by a utility function estimating downstream value.
-
From Sampled Outcomes to Capability Distributions: Rethinking Supervision for LLM Routing
DARS replaces single-shot response labels with distribution-aware supervision derived from input and output uncertainty to produce more reliable LLM routing policies.
-
AdMem: Advanced Memory for Task-solving Agents
AdMem introduces a unified bi-level memory framework with multi-agent automatic generation and reward-based long-term management that improves success on long-horizon LLM agent tasks.
-
Doppler Prompting for Stable mmWave-based Human Pose Estimation
PULSE stabilizes mmWave human pose estimation by screening Doppler motion prompts before injecting them into spatial magnitude reasoning.
-
TabEmb: Joint Semantic-Structure Embedding for Table Annotation
TabEmb decouples LLM-based semantic column embeddings from graph-based structural modeling to produce joint representations that improve table annotation tasks.
-
Align Documents to Questions: Question-Oriented Document Rewriting for Retrieval-Augmented Generation
QREAM rewrites documents to question-focused style using iterative ICL and distilled FT models, boosting RAG performance by up to 8% relative improvement.
-
CMSL: Constructive Multi-Sequence Learning for Recommendation Systems
CMSL uses a learnable module to disentangle user history into multiple pure sequences modeled with linear attention to improve recommendation performance over single-sequence approaches.
-
Target-confidence Recourse Using tSeTlin machines: TRUST
TRUST searches for minimal input changes that achieve a user-defined confidence target in PTM models, claiming perfect robustness and low cost on benchmarks versus standard boundary-crossing methods.
-
DD-GEPA: Prompt Optimization for Dialogue Disentanglement Focusing on Task Instruction and Utterance Representation
DD-GEPA decomposes and optimizes prompts with GEPA for LLM-based dialogue disentanglement, reporting accuracy gains over baseline and hand-crafted prompts on benchmarks.
-
Dependencies and Dataflow in Seed-Filter-Extend Pipelines
The paper analyzes dependencies in genome alignment pipelines and implements synthesized optimizations from four prior tools into LASTZ to reduce serial bottlenecks.
-
Cost-of-Ethics Crisis: Beliefs, Decisions, and Justifications in the Job Searches of Computer Science Students in Canada and the United States
CS students and recent grads prioritize pay and workplace culture over ethics in job searches and justify conflicting decisions with shared explanations such as money or lack of alternatives.
-
A Tree-of-Thoughts Inspired Hybrid Approach for Legal Case Judgement Summarization using LLMs
A tree-of-thoughts inspired hybrid extractive-abstractive LLM prompt yields better legal case judgment summaries than standard extractive or abstractive prompts.
-
Y-BotFrame: An Extensible Embodied Agent Framework for Quadruped Robot Assistants
Y-BotFrame is an extensible software framework that integrates multimodal perception and an LLM to map natural-language instructions to executable tasks on quadruped robots.
-
Are Researchers Being Replaced by Artificial Intelligence?
AI is shifting researchers from creators to curators of generated content, risking loss of intellectual ownership and genuine understanding of science.
-
A Pedagogical Introduction to the Unified Transform Method: The Heat Equation on a Finite Interval
The paper demonstrates the Unified Transform Method on the heat equation with Dirichlet conditions, obtaining a contour integral solution that matches data to machine precision in a Maple implementation.
-
Skills for the future software profession: beyond agentic AI!
Round-table discussions with researchers and practitioners indicate verification and validation skills will become central for software engineers in the agentic AI era.
- BetXplain: An Explanation-Annotated Dataset for Detecting Manipulative Betting Advertisements on Social Media
- Occlusion-Aware Physics-Semantic Keyframe Selection for Robust Video Editing
- QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning
- R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow