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.

Retrieval-augmented generation (RAG) has become a standard mechanism for grounding language models in external knowledge, yet conventional retrieval based on lexical or semantic similarity is poorly suited for complex reasoning tasks: a semantically similar problem may demand an entirely different solution strategy, while a superficially different problem may share the same underlying reasoning pattern. We propose Retrieval-Augmented Reinforcement Fine-Tuning (RA-RFT), a post-training framework that teaches language models to reason by analogy. RA-RFT uses gold-relevance distillation to train a retriever that ranks contexts by expected reasoning benefit rather than semantic overlap, and then fine-tunes the policy model via reinforcement fine-tuning methods with retrieved analogous demonstrations, so the model learns to leverage reasoning traces under verifiable outcome rewards. We further analyze the diversity of retrieved contexts and find that reasoning-aware retrieval surfaces complementary solution strategies that provide distinct reasoning scaffolds for individual problems. Across challenging mathematical reasoning benchmarks, RA-RFT consistently outperforms standard reinforcement fine-tuning methods. For example, it improves AIME 2025 average@32 accuracy by 7.1 and 2.8 points over GRPO for Qwen3-1.7B and Qwen3-4B respectively—suggesting that reasoning-aware retrieval is a complementary axis of improvement and orthogonal to advances in reward design or training curricula.

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.

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.

Women are often perceived as junior to their male counterparts, even within the same job titles. While there has been significant progress in the evaluation of gender bias in natural language processing (NLP), existing studies seldom investigate how biases toward gender groups change when compounded with other societal biases. In this work, we investigate how seniority impacts the degree of gender bias exhibited in pretrained neural generation models by introducing a novel framework for probing compound bias. We contribute a benchmark robustness-testing dataset spanning two domains, U.S. senatorship and professorship, created using a distant-supervision method. Our dataset includes human-written text with underlying ground truth and paired counterfactuals. We then examine GPT-2 perplexity and the frequency of gendered language in generated text. Our results show that GPT-2 amplifies bias by considering women as junior and men as senior more often than the ground truth in both domains. These results suggest that NLP applications built using GPT-2 may harm women in professional capacities.

We propose Visual News Captioner, an entity-aware model for the task of news image captioning. We also introduce Visual News, a large-scale benchmark consisting of more than one million news images along with associated news articles, image captions, author information, and other metadata. Unlike the standard image captioning task, news images depict situations where people, locations, and events are of paramount importance. Our proposed method can effectively combine visual and textual features to generate captions with richer information such as events and entities. More specifically, built upon the Transformer architecture, our model is further equipped with novel multi-modal feature fusion techniques and attention mechanisms, which are designed to generate named entities more accurately. Our method utilizes much fewer parameters while achieving slightly better prediction results than competing methods. Our larger and more diverse Visual News dataset further highlights the remaining challenges in captioning news images.

Our work aims to leverage visual feature space to pass information across languages. We show that models trained to generate textual captions in more than one language conditioned on an input image can leverage their jointly trained feature space during inference to pivot across languages. We particularly demonstrate improved quality on a caption generated from an input image, by leveraging a caption in a second language. More importantly, we demonstrate that even without conditioning on any visual input, the model demonstrates to have learned implicitly to perform to some extent machine translation from one language to another in their shared visual feature space. We show results in German-English, and Japanese-English language pairs that pave the way for using the visual world to learn a common representation for language.

Word embeddings derived from human-generated corpora inherit strong gender bias which can be further amplified by downstream models. Some commonly adopted debiasing approaches, including the seminal Hard Debias algorithm, apply post-processing procedures that project pre-trained word embeddings into a subspace orthogonal to an inferred gender subspace. We discover that semantic-agnostic corpus regularities such as word frequency captured by the word embeddings negatively impact the performance of these algorithms. We propose a simple but effective technique, Double Hard Debias, which purifies the word embeddings against such corpus regularities prior to inferring and removing the gender subspace. Experiments on three bias mitigation benchmarks show that our approach preserves the distributional semantics of the pre-trained word embeddings while reducing gender bias to a significantly larger degree than prior approaches.

In this paper we introduce Chat-crowd, an interactive environment for visual layout composition via conversational interactions. Chat-crowd supports multiple agents with two conversational roles: agents who play the role of a designer are in charge of placing objects in an editable canvas according to instructions or commands issued by agents with a director role. The system can be integrated with crowdsourcing platforms for both synchronous and asynchronous data collection and is equipped with comprehensive quality controls on the performance of both types of agents. We expect that this system will be useful to build multimodal goal-oriented dialog tasks that require spatial and geometric reasoning.

In this paper, we quantify, analyze and mitigate gender bias exhibited in ELMo’s contextualized word vectors. First, we conduct several intrinsic analyses and find that (1) training data for ELMo contains significantly more male than female entities, (2) the trained ELMo embeddings systematically encode gender information and (3) ELMo unequally encodes gender information about male and female entities. Then, we show that a state-of-the-art coreference system that depends on ELMo inherits its bias and demonstrates significant bias on the WinoBias probing corpus. Finally, we explore two methods to mitigate such gender bias and show that the bias demonstrated on WinoBias can be eliminated.

Recent advances in data-driven machine learning techniques (e.g., deep neural networks) have revolutionized many natural language processing applications. These approaches automatically learn how to make decisions based on the statistics and diagnostic information from large amounts of training data. Despite the remarkable accuracy of machine learning in various applications, learning algorithms run the risk of relying on societal biases encoded in the training data to make predictions. This often occurs even when gender and ethnicity information is not explicitly provided to the system because learning algorithms are able to discover implicit associations between individuals and their demographic information based on other variables such as names, titles, home addresses, etc. Therefore, machine learning algorithms risk potentially encouraging unfair and discriminatory decision making and raise serious privacy concerns. Without properly quantifying and reducing the reliance on such correlations, broad adoption of these models might have the undesirable effect of magnifying harmful stereotypes or implicit biases that rely on sensitive demographic attributes.

In this tutorial, we will review the history of bias and fairness studies in machine learning and language processing and present recent community effort in quantifying and mitigating bias in natural language processing models for a wide spectrum of tasks, including word embeddings, co-reference resolution, machine translation, and vision-and-language tasks. In particular, we will focus on the following topics:

+ Definitions of fairness and bias.

+ Data, algorithms, and models that propagate and even amplify social bias to NLP applications and metrics to quantify these biases.

+ Algorithmic solutions; learning objective; design principles to prevent social bias in NLP systems and their potential drawbacks.

The tutorial will bring researchers and practitioners to be aware of this issue, and encourage the research community to propose innovative solutions to promote fairness in NLP.

In this paper, we introduce a new benchmark for co-reference resolution focused on gender bias, WinoBias. Our corpus contains Winograd-schema style sentences with entities corresponding to people referred by their occupation (e.g. the nurse, the doctor, the carpenter). We demonstrate that a rule-based, a feature-rich, and a neural coreference system all link gendered pronouns to pro-stereotypical entities with higher accuracy than anti-stereotypical entities, by an average difference of 21.1 in F1 score. Finally, we demonstrate a data-augmentation approach that, in combination with existing word-embedding debiasing techniques, removes the bias demonstrated by these systems in WinoBias without significantly affecting their performance on existing datasets.

Language is increasingly being used to de-fine rich visual recognition problems with supporting image collections sourced from the web. Structured prediction models are used in these tasks to take advantage of correlations between co-occurring labels and visual input but risk inadvertently encoding social biases found in web corpora. In this work, we study data and models associated with multilabel object classification and visual semantic role labeling. We find that (a) datasets for these tasks contain significant gender bias and (b) models trained on these datasets further amplify existing bias. For example, the activity cooking is over 33% more likely to involve females than males in a training set, and a trained model further amplifies the disparity to 68% at test time. We propose to inject corpus-level constraints for calibrating existing structured prediction models and design an algorithm based on Lagrangian relaxation for collective inference. Our method results in almost no performance loss for the underlying recognition task but decreases the magnitude of bias amplification by 47.5% and 40.5% for multilabel classification and visual semantic role labeling, respectively。

Generating captions for images is a task that has recently received considerable attention. Another type of visual inputs are abstract scenes or object layouts where the only information provided is a set of objects and their locations. This type of imagery is commonly found in many applications in computer graphics, virtual reality, and storyboarding. We explore in this paper OBJ2TEXT, a sequence-to-sequence model that encodes a set of objects and their locations as an input sequence using an LSTM network, and decodes this representation using an LSTM language model. We show in our paper that this model despite using a sequence encoder can effectively represent complex spatial object-object relationships and produce descriptions that are globally coherent and semantically relevant. We test our approach for the task of describing object layouts in the MS-COCO dataset by producing sentences given only object annotations. We additionally show that our model combined with a state-of-the-art object detector can improve the accuracy of an image captioning model.

We present a new tree based approach to composing expressive image descriptions that makes use of naturally occuring web images with captions. We investigate two related tasks: image caption generalization and generation, where the former is an optional subtask of the latter. The high-level idea of our approach is to harvest expressive phrases (as tree fragments) from existing image descriptions, then to compose a new description by selectively combining the extracted (and optionally pruned) tree fragments. Key algorithmic components are tree composition and compression, both integrating tree structure with sequence structure. Our proposed system attains significantly better performance than previous approaches for both image caption generalization and generation. In addition, our work is the first to show the empirical benefit of automatically generalized captions for composing natural image descriptions.