Search Results for author:
Found 14 papers, 10 papers with code
Bayesian Teaching Enables Probabilistic Reasoning in Large Language Models
To evaluate whether contemporary LLMs are able to do so, we use the Bayesian inference framework from probability theory, which lays out the optimal way to update an agent's beliefs as it receives new information.
The Surprising Effectiveness of Test-Time Training for Few-Shot Learning
Language models (LMs) have shown impressive performance on tasks within their training distribution, but often struggle with structurally novel tasks even when given a small number of in-context task examples.
Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps
We find that a linear classifier based on these lookback ratio features is as effective as a richer detector that utilizes the entire hidden states of an LLM or a text-based entailment model.
Learning to Reason via Program Generation, Emulation, and Search
CoGEX works by (1) training LMs to generate pseudo-programs, (2) teaching them to emulate their generated program's execution, including those leaf functions, allowing the LM's knowledge to fill in the execution gaps; and (3) using them to search over many programs to find an optimal one.
Bias Amplification in Language Model Evolution: An Iterated Learning Perspective
With the widespread adoption of Large Language Models (LLMs), the prevalence of iterative interactions among these models is anticipated to increase.
Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement
The ability to derive underlying principles from a handful of observations and then generalize to novel situations -- known as inductive reasoning -- is central to human intelligence.
Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks
The impressive performance of recent language models across a wide range of tasks suggests that they possess a degree of abstract reasoning skills.
QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Tracking
In this paper, we present Quasi-Dense Similarity Learning, which densely samples hundreds of object regions on a pair of images for contrastive learning.
Ranked #4 on
Multiple Object Tracking
on BDD100K val
Generate-and-Retrieve: use your predictions to improve retrieval for semantic parsing
Then, it retrieves exemplars with outputs similar to the preliminary prediction which are used to generate a final prediction.
Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsing
Meanwhile, recent work has shown considerable improvements on many NLP tasks from model scaling.
Improving Compositional Generalization with Latent Structure and Data Augmentation
Generic unstructured neural networks have been shown to struggle on out-of-distribution compositional generalization.
Visually Grounded Concept Composition
We investigate ways to compose complex concepts in texts from primitive ones while grounding them in images.
Systematic Generalization on gSCAN: What is Nearly Solved and What is Next?
We analyze the grounded SCAN (gSCAN) benchmark, which was recently proposed to study systematic generalization for grounded language understanding.
Ranked #4 on
Compositional Generalization (AVG)
on ReaSCAN
Compositional Generalization (AVG)
Systematic Generalization
Quasi-Dense Similarity Learning for Multiple Object Tracking
Compared to methods with similar detectors, it boosts almost 10 points of MOTA and significantly decreases the number of ID switches on BDD100K and Waymo datasets.
Ranked #1 on
One-Shot Object Detection
on PASCAL VOC 2012 val
