We introduce HypoExplore, an agentic framework that formulates model discovery as a hypothesis-driven scientific inquiry. Given a human-specified high-level research direction, HypoExplore ideates, implements, evaluates, and improves neural architectures through evolutionary branching. Hypotheses are generated using a large language model by selecting a parent hypothesis to build upon, guided by a dual strategy that balances exploiting validated principles with resolving uncertain ones. Our proposed framework maintains a Trajectory Tree that records the lineage of all proposed architectures, and a Hypothesis Memory Bank that actively tracks associated confidence scores acquired through experimental evidence. After each experiment, multiple feedback agents analyze the results from different perspectives and consolidate their findings into hypothesis confidence updates. Under minimal research directions, HypoExplore discovers a model that achieves top results on two medical imaging tasks on MedMNIST, an improved encoder for named entity recognition on FiNER-ORD, and a lightweight 0.7M parameter model on CIFAR-10 that reaches 94.1% accuracy and transfers well to other benchmarks. Our analysis of hypothesis confidence scores across evolutionary lineages suggest that HypoExplore not only discovers stronger architectures, but can help build a genuine understanding of the design space.

Existing visual grounding benchmarks primarily evaluate alignment between image regions and literal referring expressions, where models can often succeed by matching a prominent named category. This leaves a complementary but under-examined setting: scenario-based visual grounding, where the target must be inferred from roles, intentions, and relational context rather than explicit object naming alone. We introduce Referring Scenario Comprehension (RSC), a benchmark designed to study this setting. RSC queries describe roles, goals, and contextual cues, and deliberately reference distractor objects to reduce lexical shortcutting. Each instance is annotated with interpretable difficulty tags for uniqueness, clutter, size, overlap, and position, which expose distinct failure modes and support fine-grained analysis. RSC contains approximately 31k training examples, 4k in-domain test examples, and a 3k out-of-distribution split with unseen object categories to test generalization beyond category co-occurrence. We further propose ScenGround, a curriculum reasoning method serving as a reference point for this setting, combining supervised warm-starting with difficulty-aware reinforcement learning. Experiments show that scenario-based queries expose systematic shortcut failures in current models that standard benchmarks do not reveal, and that curriculum training improves performance on challenging slices and transfers robust improvement to standard benchmarks.

This paper investigates the optimal selection and fusion of feature encoders across multiple modalities and combines these in one neural network to improve sentiment detection. We compare different fusion methods and examine the impact of multi-loss training within the multi-modality fusion network, identifying surprisingly important findings relating to subnet performance. We have also found that integrating context significantly enhances model performance. Our best model achieves state-of-the-art performance for three datasets (CMU-MOSI, CMU-MOSEI and CH-SIMS). These results suggest a roadmap toward an optimized feature selection and fusion approach for enhancing sentiment detection in neural networks.

Visual Programming has recently emerged as an alternative to end-to-end black-box visual reasoning models. This type of method leverages Large Language Models (LLMs) to generate the source code for an executable computer program that solves a given problem. This strategy has the advantage of offering an interpretable reasoning path and does not require finetuning a model with task-specific data. We propose PropTest, a general strategy that improves visual programming by further using an LLM to generate code that tests for visual properties in an initial round of proposed solutions. Our method generates tests for data-type consistency, output syntax, and semantic properties. PropTest achieves comparable results to state-of-the-art methods while using publicly available LLMs. This is demonstrated across different benchmarks on visual question answering and referring expression comprehension. Particularly, PropTest improves ViperGPT by obtaining 46.1% accuracy (+6.0%) on GQA using Llama3-8B and 59.5% (+8.1%) on RefCOCO+ using CodeLlama-34B.