328 citations · 1.6k across the 61 of their papers we have counts for
61 papers
Can Models Learn Skill Composition from Examples?
Haoyu Zhao, Simran Kaur, Dingli Yu +2
As large language models (LLMs) become increasingly advanced, their ability to exhibit compositional generalization -- the capacity to combine learned skills in novel ways not enco…
Zero-Shot Object-Centric Representation Learning
Aniket Didolkar, Andrii Zadaianchuk, Anirudh Goyal +4
The goal of object-centric representation learning is to decompose visual scenes into a structured representation that isolates the entities. Recent successes have shown that objec…
Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning
Simran Kaur, Simon Park, Anirudh Goyal +1
We introduce Instruct-SkillMix, an automated approach for creating diverse, high quality SFT data for instruction-following. The pipeline involves two stages, each leveraging an ex…
AI-Assisted Generation of Difficult Math Questions
Vedant Shah, Dingli Yu, Kaifeng Lyu +8
Current LLM training positions mathematical reasoning as a core capability. With publicly available sources fully tapped, there is unmet demand for diverse and challenging math que…
Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning
Yuxi Xie, Anirudh Goyal, Wenyue Zheng +4
We introduce an approach aimed at enhancing the reasoning capabilities of Large Language Models (LLMs) through an iterative preference learning process inspired by the successful s…
Bayesian-LoRA: LoRA based Parameter Efficient Fine-Tuning using Optimal Quantization levels and Rank Values trough Differentiable Bayesian Gates
Cristian Meo, Ksenia Sycheva, Anirudh Goyal +1
It is a common practice in natural language processing to pre-train a single model on a general domain and then fine-tune it for downstream tasks. However, when it comes to Large L…
Learning Beyond Pattern Matching? Assaying Mathematical Understanding in LLMs
Siyuan Guo, Aniket Didolkar, Nan Rosemary Ke +3
We are beginning to see progress in language model assisted scientific discovery. Motivated by the use of LLMs as a general scientific assistant, this paper assesses the domain kno…
Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving
Aniket Didolkar, Anirudh Goyal, Nan Rosemary Ke +7
Metacognitive knowledge refers to humans' intuitive knowledge of their own thinking and reasoning processes. Today's best LLMs clearly possess some reasoning processes. The paper g…
Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling
Yiran Zhao, Wenyue Zheng, Tianle Cai +4
Safety of Large Language Models (LLMs) has become a critical issue given their rapid progresses. Greedy Coordinate Gradient (GCG) is shown to be effective in constructing adversari…
Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates
Kaifeng Lyu, Haoyu Zhao, Xinran Gu +3
Public LLMs such as the Llama 2-Chat underwent alignment training and were considered safe. Recently Qi et al. [2024] reported that even benign fine-tuning on seemingly safe datase…
Unlearning via Sparse Representations
Vedant Shah, Frederik Träuble, Ashish Malik +5
Machine \emph{unlearning}, which involves erasing knowledge about a \emph{forget set} from a trained model, can prove to be costly and infeasible by existing techniques. We propose…
Physical Reasoning and Object Planning for Household Embodied Agents
Ayush Agrawal, Raghav Prabhakar, Anirudh Goyal +1
In this study, we explore the sophisticated domain of task planning for robust household embodied agents, with a particular emphasis on the intricate task of selecting substitute o…
Skill-Mix: a Flexible and Expandable Family of Evaluations for AI models
Dingli Yu, Simran Kaur, Arushi Gupta +3
With LLMs shifting their role from statistical modeling of language to serving as general-purpose AI agents, how should LLM evaluations change? Arguably, a key ability of an AI age…
A Theory for Emergence of Complex Skills in Language Models
Sanjeev Arora, Anirudh Goyal
A major driver of AI products today is the fact that new skills emerge in language models when their parameter set and training corpora are scaled up. This phenomenon is poorly und…
Cycle Consistency Driven Object Discovery
Aniket Didolkar, Anirudh Goyal, Yoshua Bengio
Developing deep learning models that effectively learn object-centric representations, akin to human cognition, remains a challenging task. Existing approaches facilitate object di…
Spotlight Attention: Robust Object-Centric Learning With a Spatial Locality Prior
Ayush Chakravarthy, Trang Nguyen, Anirudh Goyal +2
The aim of object-centric vision is to construct an explicit representation of the objects in a scene. This representation is obtained via a set of interchangeable modules called \…
DiscoGen: Learning to Discover Gene Regulatory Networks
Nan Rosemary Ke, Sara-Jane Dunn, Jorg Bornschein +11
Accurately inferring Gene Regulatory Networks (GRNs) is a critical and challenging task in biology. GRNs model the activatory and inhibitory interactions between genes and are inhe…
TC-VAE: Uncovering Out-of-Distribution Data Generative Factors
Cristian Meo, Anirudh Goyal, Justin Dauwels
Uncovering data generative factors is the ultimate goal of disentanglement learning. Although many works proposed disentangling generative models able to uncover the underlying gen…
Leveraging the Third Dimension in Contrastive Learning
Sumukh Aithal, Anirudh Goyal, Alex Lamb +2
Self-Supervised Learning (SSL) methods operate on unlabeled data to learn robust representations useful for downstream tasks. Most SSL methods rely on augmentations obtained by tra…
Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learning
Riashat Islam, Hongyu Zang, Anirudh Goyal +6
Goal-conditioned reinforcement learning (RL) is a promising direction for training agents that are capable of solving multiple tasks and reach a diverse set of objectives. How to \…
GFlowOut: Dropout with Generative Flow Networks
Dianbo Liu, Moksh Jain, Bonaventure Dossou +10
Bayesian Inference offers principled tools to tackle many critical problems with modern neural networks such as poor calibration and generalization, and data inefficiency. However,…
Stateful active facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning
Dianbo Liu, Vedant Shah, Oussama Boussif +6
In cooperative multi-agent reinforcement learning, a team of agents works together to achieve a common goal. Different environments or tasks may require varying degrees of coordina…
Discrete Key-Value Bottleneck
Frederik Träuble, Anirudh Goyal, Nasim Rahaman +4
Deep neural networks perform well on classification tasks where data streams are i.i.d. and labeled data is abundant. Challenges emerge with non-stationary training data streams su…
On the Generalization and Adaption Performance of Causal Models
Nino Scherrer, Anirudh Goyal, Stefan Bauer +2
Learning models that offer robust out-of-distribution generalization and fast adaptation is a key challenge in modern machine learning. Modelling causal structure into neural netwo…