Papers by Joao Magalhaes

7 papers
Generating Coherent Sequences of Visual Illustrations for Real-World Manual Tasks (2024.acl-long)

Copied to clipboard

Challenge: Large Vision/Language Models (LVLMs) are less capable of generating accompanying image sequences.
Approach: They propose a method that integrates a Latent Diffusion Model (LDM) with an LLM to generate captions to maintain semantic coherence of the sequence.
Outcome: The proposed method is preferred by humans in 46.6% of the cases against 26.6% for the second best method.
Dwell in the Beginning: How Language Models Embed Long Documents for Dense Retrieval (2024.acl-short)

Copied to clipboard

Challenge: Existing studies have shown that Transformer-based language models lose information in the middle of input sequences, especially in the context of web document retrieval.
Approach: They examine position biases at multiple stages of the training pipeline for an encoder-decoder neural retrieval model, namely language model pre-training, contrastive pre- training, and contrastive fine-tuning.
Outcome: The proposed model generates embeddings that better capture the beginning of the input content, with fine-tuning further aggravating this effect.
Plan-Grounded Large Language Models for Dual Goal Conversational Settings (2024.eacl-long)

Copied to clipboard

Challenge: Existing studies show that LLMs can follow user instructions, but it is unclear how they can lead a plan-grounded conversation in mixed-initiative settings where instructions flow in both directions of the conversation.
Approach: They propose a dual-purpose mixed-initiative conversational setting where the LLM grounds the conversation on an arbitrary plan and seeks to satisfy both a procedural plan and user instructions.
Outcome: The proposed model achieves 2.1x improvement over a strong baseline and good generalization to unseen domains.
Show and Guide: Instructional-Plan Grounded Vision and Language Model (2024.emnlp-main)

Copied to clipboard

Challenge: Existing plans-following language models (LLMs) are not capable of multimodal input and output, resulting in inconsistent performance on multimodal tasks.
Approach: They propose a multimodal plan-following language model that integrates both textual plans and visual information to bring cross-modality to instructional tasks.
Outcome: The proposed model performs well on multimodal and textual dialogue in a plan-grounded setting.
Multi-trait User Simulation with Adaptive Decoding for Conversational Task Assistants (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to model conversational traits are costly and time consuming.
Approach: They propose a method that generates diverse user profiles at decoding-time by sampling from trait-specific Language Models.
Outcome: The proposed method generates diverse user profiles at decoding-time without fine-tuning.
Language Models Can be Efficiently Steered via Minimal Embedding Layer Transformations (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for fine-tuning Large Language Models (LLMs) neglect the embedding layer.
Approach: They propose a PEFT approach that modifies input embeddings without altering hidden layers.
Outcome: Experiments show that TinyTE modifies embeddings without altering hidden layers . the proposed approach achieves competitive performance while requiring 0.0001% of parameters .
VIGiA: Instructional Video Guidance via Dialogue Reasoning and Retrieval (2026.findings-eacl)

Copied to clipboard

Challenge: Existing models focus on text-only guidance or treat vision and language in isolation.
Approach: They propose a multimodal dialogue model that supports grounded, plan-aware dialogue . they use a dataset with rich video dialogues aligned with cooking and DIY plans .
Outcome: The proposed model outperforms existing models on all tasks in a conversational plan guidance setting, reaching over 90% accuracy on plan-aware VQA.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations