Joint Generation and Evaluation
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Self-Evolving Deep Research via Joint Generation and Evaluation
arXiv:2606.04507v1 Announce Type: new Abstract: Large Language Models (LLMs) have become increasingly adopted in daily applications, with deep research standing out as a particularly important capability. Unlike traditional question-answering (QA) tasks, deep research report generation lacks definitive ground-truth, making reward design inherently unverifiable and limiting effective reinforcement learning. Existing approaches mitigate this challenge with LLM-as-a-judge and query-dependent...
Do Joint Audio-Video Generation Models Understand Physics?
arXiv:2605.07061v2 Announce Type: replace Abstract: Joint audio-video generation models are rapidly approaching professional production quality, raising a central question: do they understand audio-visual physics, or merely generate plausible sounds and frames that violate real-world consistency? We introduce AV-Phys Bench, a benchmark for evaluating physical commonsense in joint audio-video generation. AV-Phys Bench tests models across three scene categories: Steady State, Event Transition,...
Flow-HOA: Generative Joint Optimization for Ambisonics Encoding via Flow Matching
Announce Type: new Abstract: Higher-Order Ambisonics (HOA) encoding from sparse, irregular microphone arrays remains a critical challenge for consumer spatial audio capture in immersive communication and XR. We propose Flow-HOA, a generative framework that jointly optimizes a multi-dimensional objective encompassing time-domain, spectral, and spatial fidelity while producing a deployable, time-invariant bank of Finite Impulse Response (FIR) encoding filters. Using conditional flow matching,...
FEM-Bench: A Structured Scientific Reasoning Benchmark for Evaluating Code-Generating LLMs
arXiv:2512.20732v2 Announce Type: replace Abstract: As LLMs advance their reasoning capabilities about the physical world, the absence of rigorous benchmarks for evaluating their ability to generate scientifically valid physical models has become a critical gap. Computational mechanics, which develops and applies mathematical models and numerical methods to predict the behavior of physical systems under forces, deformation, and constraints, provides an ideal foundation for structured...
Can LLMs understand LilyPond? A benchmark for symbolic music generation and understanding
Announce Type: new Abstract: Symbolic music evaluation for large language models remains fragmented across representations, datasets, and metrics. We introduce LilyBench, a LilyPond-based benchmark that jointly evaluates symbolic music generation and music understanding on the same family of open-weight LLMs. The benchmark includes a 200-prompt generation suite and ten understanding tasks adapted from ABC-Eval, covering syntax, metadata prediction, structural sequencing, and music recognition.
Evaluating the Representation Space of Diffusion Models via Self-Supervised Principles
arXiv:2606.09718v1 Announce Type: new Abstract: Diffusion models have demonstrated remarkable generative capabilities and have also emerged as powerful self-supervised representation learners, yet the connection between these two abilities remains less explored. Drawing inspiration from self-supervised learning (SSL), we introduce a framework for jointly evaluating the representation and generation capabilities of diffusion models. Specifically, we decompose features into invariant and...
Unified Video-Action Joint Denoising for Dexterous Action and Data Generation
arXiv:2606.03868v1 Announce Type: new Abstract: Recent world action models leverage video foundation models by aligning broad visual-dynamics priors with executable robot actions. We revisit this alignment from a distributional perspective.
CatalyticMLLM: A Graph-Text Multimodal Large Language Model for Catalytic Materials
arXiv:2605.17254v3 Announce Type: replace Abstract: Property prediction and inverse structural design of catalytic materials are typically modeled as two independent tasks: the former predicts target properties from given structures, whereas the latter generates candidate structures according to desired properties. Although the decoupled paradigm facilitates the implementation of a ``generation--evaluation--screening'' workflow, the inconsistency between the generative model and the property...
ParetoPilot: Zero-Surrogate Offline Multi-Objective Optimization via Infer-Perturb-Guide Diffusion
Announce Type: new Abstract: Offline multi-objective optimization (Offline MOO) aims to discover novel Pareto-optimal designs based on static datasets without expensive environment interactions. While recent generative methods have achieved notable success, they predominantly rely on external surrogate models. This dependency introduces significant computational overhead, suffers from deceptive evaluations, and deviates from the prevailing paradigm of jointly training mainstream generative...
Foley-Omni: A Unified Multimodal Generation Model from Task-Level Audio Synthesis to Complete Video Soundtrack Generation
Announce Type: new Abstract: Recent unified audio generation models can support diverse tasks across speech, sound effects, and music, but most of them still focus on isolated task-level synthesis. However, real video production often requires multiple components of a complete audio track to be generated jointly and consistently for the same video. We present Foley-Omni, a unified multimodal audio generation model that extends isolated task-level synthesis to complete video soundtrack...