1 citations · 1 across the 10 of their papers we have counts for
17 papers
KEEP-Bench: Evaluating Evidence Preservation in Context Compression
Ziqing Man, Di Wu, Jia-Chen Gu +3
Context compression improves long-context efficiency but may introduce faithfulness issues through an information bottleneck. Existing evaluations rely on QA metrics, but a reader…
Lean Graph Search for Formal Theorem Proving
Yihan Xu, Jia-Chen Gu, Junyi Zhang +7
Retrieving relevant lemmas is crucial for formal theorem proving, enabling provers to build machine-checkable proofs from established mathematical results. Recent retrieval systems…
DuoDiscover: Scaling Autonomous Discovery Beyond the Evaluation Bottleneck
Shubham Agarwal, Akshat Gupta, Mike Heddes +21
Evaluation has been central to advances in AI, and it is equally critical to autonomous discovery. Yet scaling autonomous discovery to real-world engineering challenges faces a fun…
Unsupervised Maneuver-Aware Acoustic Fault Detection for Autonomous Drones
Ali M Ali, Ziyi Tang, Nurdaulet Nazarbay +1
This paper presents a maneuver-aware acoustic fault detection framework for autonomous drones that integrates Noise2Noise-inspired deep learning denoising with maneuver-conditioned…
Continual Graph Memory for Mathematical Research Agents
Junyi Zhang, Jinxi Yu, Eric Hanchen Jiang +14
Using frontier agent harnesses to tackle mathematical research problems has emerged as an effective means of advancing mathematics. However, solving frontier problems in mathematic…
Planned Test-Time Scaling with Coordinated Reasoning Paths
Xueqing Wu, Langxing Bai, Hritik Bansal +5
Test-time scaling with parallel branches is widely adopted to improve performance on challenging reasoning tasks. The predominant approach, repeated sampling, draws branches indepe…
TwinICL: Diagnosing Multimodal In-Context Learning through Paired Counterfactuals
Zihan Xue, Po-Yi Lu, Serhii Honcharenko +5
In-context learning (ICL) enables models to infer tasks from demonstrations, but existing benchmarks generally lack matched text and image versions needed to compare ICL performanc…
PaperBanana-Interact: Scientific Diagram Refinement with Multi-Turn Human Feedback
Xueqing Wu, Ashwin Balasubramanian, Bingxuan Li +7
Recent efforts have aimed to automate scientific diagram generation from paper content (Lin et al., 2026; Zhu et al., 2026a). However, fully satisfying an author's visual and commu…
Nexus : An Agentic Framework for Context-Aware Time Series Forecasting
Sarkar Snigdha Sarathi Das, Palash Goyal, Mihir Parmar +6
Language models have emerged as highly capable reasoners, yet their performance in time series forecasting remains uneven across domains and levels of contextual grounding. This is…
LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues
Di Wu, Zixiang Ji, Asmi Kawatkar +4
Long-term memory is crucial for agents in specialized web environments, where success depends on recalling interface affordances, state dynamics, workflows, and recurring failure m…
TaoBench: Do Automated Theorem Prover LLMs Generalize Beyond MathLib?
Alexander K Taylor, Junyi Zhang, Ethan Ji +10
Automated theorem proving (ATP) benchmarks largely consist of problems formalized in MathLib, so current ATP training and evaluation are heavily biased toward MathLib's definitiona…
FronTalk: Benchmarking Front-End Development as Conversational Code Generation with Multi-Modal Feedback
Xueqing Wu, Zihan Xue, Da Yin +4
We present FronTalk, a benchmark for front-end code generation that pioneers the study of a unique interaction dynamic: conversational code generation with multi-modal feedback. In…
DialectGen: Benchmarking and Improving Dialect Robustness in Multimodal Generation
Yu Zhou, Sohyun An, Haikang Deng +5
Contact languages like English exhibit rich regional variations in the form of dialects, which are often used by dialect speakers interacting with generative models. However, can m…
SafeWorld: Geo-Diverse Safety Alignment
Da Yin, Haoyi Qiu, Kung-Hsiang Huang +2
In the rapidly evolving field of Large Language Models (LLMs), ensuring safety is a crucial and widely discussed topic. However, existing works often overlook the geo-diversity of…
VISCO: Benchmarking Fine-Grained Critique and Correction Towards Self-Improvement in Visual Reasoning
Xueqing Wu, Yuheng Ding, Bingxuan Li +4
The ability of large vision-language models (LVLMs) to critique and correct their reasoning is an essential building block towards their self-improvement. However, a systematic ana…
Verbalized Representation Learning for Interpretable Few-Shot Generalization
Cheng-Fu Yang, Da Yin, Wenbo Hu +4
Humans recognize objects after observing only a few examples, a remarkable capability enabled by their inherent language understanding of the real-world environment. Developing ver…
Guiding Through Complexity: What Makes Good Supervision for Hard Math Reasoning Tasks?
Xuan He, Da Yin, Nanyun Peng
How can "weak teacher models" such as average human annotators or existing AI systems, effectively supervise LLMs to improve performance on hard reasoning tasks, especially those t…