121 citations · 142 across the 18 of their papers we have counts for
21 papers
Question Begets Question: Self-Evolving Curriculum for Reinforcement Fine-Tuning on Competition Mathematics
Longtian Bao, Jianyou Wang, Yang Zhang +2
Teaching a language model a skill it has not mastered is obstructed by three recurring difficulties: training data is scarce, ground-truth reasoning traces are usually unavailable,…
DeepImagine: Clinical Trial Outcome Prediction via Stepwise Local Counterfactual Imaginations
Youze Zheng, Jianyou Wang, Yuhan Chen +8
Predicting the outcomes of prospective clinical trials remains a major challenge. Clinical trial outcomes result from complex interactions among experimental factors such as drug i…
CT Open: An Open-Access, Uncontaminated, Live Platform for the Open Challenge of Clinical Trial Outcome Prediction
Jianyou Wang, Youze Zheng, Longtian Bao +11
Scientists have long sought to accurately predict outcomes of real-world events before they happen. Can AI systems do so more reliably? We study this question through clinical tria…
Quiet Feature Learning in Algorithmic Tasks
Prudhviraj Naidu, Zixian Wang, Leon Bergen +1
We train Transformer-based language models on ten foundational algorithmic tasks and observe pronounced phase transitions in their loss curves that deviate from established power-l…
EvidenceBench: A Benchmark for Extracting Evidence from Biomedical Papers
Jianyou Wang, Weili Cao, Kaicheng Wang +13
We study the task of automatically finding evidence relevant to hypotheses in biomedical papers. Finding relevant evidence is an important step when researchers investigate scienti…
Single-Pass Document Scanning for Question Answering
Weili Cao, Jianyou Wang, Youze Zheng +5
Handling extremely large documents for question answering is challenging: chunk-based embedding methods often lose track of important global context, while full-context transformer…
Local Enumeration: The Not-All-Equal Case
Mohit Gurumukhani, Ramamohan Paturi, Michael Saks +1
Gurumukhani et al. (CCC'24) proposed the local enumeration problem Enum(k, t) as an approach to break the Super Strong Exponential Time Hypothesis (SSETH): for a natural number …
On Extremal Properties of k-CNF: Capturing Threshold Functions
Mohit Gurumukhani, Marvin Künnemann, Ramamohan Paturi
We consider a basic question on the expressiveness of -CNF formulas: How well can -CNF formulas capture threshold functions? Specifically, what is the largest number of assig…
Measuring Risk of Bias in Biomedical Reports: The RoBBR Benchmark
Jianyou Wang, Weili Cao, Longtian Bao +6
Systems that answer questions by reviewing the scientific literature are becoming increasingly feasible. To draw reliable conclusions, these systems should take into account the qu…
Dissociation of Faithful and Unfaithful Reasoning in LLMs
Evelyn Yee, Alice Li, Chenyu Tang +3
Large language models (LLMs) often improve their performance in downstream tasks when they generate Chain of Thought reasoning text before producing an answer. We investigate how L…
BIRCO: A Benchmark of Information Retrieval Tasks with Complex Objectives
Xiaoyue Wang, Jianyou Wang, Weili Cao +3
We present the Benchmark of Information Retrieval (IR) tasks with Complex Objectives (BIRCO). BIRCO evaluates the ability of IR systems to retrieve documents given multi-faceted us…
Local Enumeration and Majority Lower Bounds
Mohit Gurumukhani, Ramamohan Paturi, Pavel Pudlák +2
Depth-3 circuit lower bounds and -SAT algorithms are intimately related; the state-of-the-art -circuit lower bound and the -SAT algorithm are based on the same combina…
IR2: Information Regularization for Information Retrieval
Jianyou Wang, Kaicheng Wang, Xiaoyue Wang +3
Effective information retrieval (IR) in settings with limited training data, particularly for complex queries, remains a challenging task. This paper introduces IR2, Information Re…
DORIS-MAE: Scientific Document Retrieval using Multi-level Aspect-based Queries
Jianyou Wang, Kaicheng Wang, Xiaoyue Wang +3
In scientific research, the ability to effectively retrieve relevant documents based on complex, multifaceted queries is critical. Existing evaluation datasets for this task are li…
On the Fine-grained Complexity of One-Dimensional Dynamic Programming
Marvin Künnemann, Ramamohan Paturi, Stefan Schneider
In this paper, we investigate the complexity of one-dimensional dynamic programming, or more specifically, of the Least-Weight Subsequence (LWS) problem: Given a sequence of da…
Subquadratic Algorithms for Succinct Stable Matching
Marvin Künnemann, Daniel Moeller, Ramamohan Paturi +1
We consider the stable matching problem when the preference lists are not given explicitly but are represented in a succinct way and ask whether the problem becomes computationally…
0-1 Integer Linear Programming with a Linear Number of Constraints
Russell Impagliazzo, Shachar Lovett, Ramamohan Paturi +1
We give an exact algorithm for the 0-1 Integer Linear Programming problem with a linear number of constraints that improves over exhaustive search by an exponential factor. Specifi…
A Satisfiability Algorithm for Sparse Depth Two Threshold Circuits
Russell Impagliazzo, Ramamohan Paturi, Stefan Schneider
We give a nontrivial algorithm for the satisfiability problem for cn-wire threshold circuits of depth two which is better than exhaustive search by a factor 2^{sn} where s= 1/c^{O(…
Experimental study of the impact of historical information in human coordination
Manuel Cebrian, Ramamohan Paturi, Daniel Ricketts
We perform laboratory experiments to elucidate the role of historical information in games involving human coordination. Our approach follows prior work studying human network coor…
On Problems as Hard as CNFSAT
Marek Cygan, Holger Dell, Daniel Lokshtanov +6
The field of exact exponential time algorithms for NP-hard problems has thrived over the last decade. While exhaustive search remains asymptotically the fastest known algorithm for…
A Satisfiability Algorithm for AC
Russell Impagliazzo, William Matthews, Ramamohan Paturi
We consider the problem of efficiently enumerating the satisfying assignments to $\AC^0$ circuits. We give a zero-error randomized algorithm which takes an $\AC^0$ circuit as input…