2 citations · 2 across the 19 of their papers we have counts for
23 papers
Do Rollups Self-Organize? Multi-Agent Reinforcement Learning in the EIP-4844 Blob Fee Market
Alessio Brini
EIP-4844 gave Ethereum rollups a separate fee dimension for data, governed by a multiplicative update rule that targets three ``blobs'' per block. Whether this target is reached de…
Correcting WHERE, Preserving HOW: Compositional Generalization for Vision-Language-Action Models via Referential Guidance
Yanyan Zhang, Disheng Liu, Xinpeng Li +8
While Vision-Language-Action (VLA) models enable flexible action generation, their generalization across diverse environmental elements, including manipulated objects, destinations…
How to Loop MoE: Flatten the Experts, Untie the Attention
Shouren Wang, Chuang Ma, Mohsen Hariri +6
Looped Transformers reuse one block of layers several times: by spending extra computation they push a model of fixed size further, and so use its parameters more fully; while spar…
Beyond Solver Verdicts: Generative Reward Models for Autoformalization
Vikash Singh, Debargha Ganguly, Aman Goel +5
Neurosymbolic systems rely on mathematical solvers to guarantee reasoning correctness, yet solvers are fundamentally blind to whether a formal translation maintains strict referenc…
StochBench: A Domain-Specific Benchmark for Stochastic Processes in Lean
Idan Davidovich, Debargha Ganguly, Vikash Singh +1
Leading benchmarks for formal theorem proving with large language models are small collections drawn from competition math, such as the IMO and Putnam, that poorly represent field-…
Test-Time Scaling in Reasoning LLMs: Inference Regimes, Evaluation, and Reproducibility
Mohsen Hariri, Weicong Chen, Nahal Shahini +11
Large language models can solve harder reasoning problems with more inference-time compute. The term "test-time scaling," however, covers several inference algorithms: extending de…
Auditing Cross-Lingual Fairness in Language Model Watermarking
Alexander Nemecek, Osama Zafar, Debargha Ganguly +3
Watermarking schemes for large language model output are evaluated almost exclusively on English text using each scheme's detection threshold and a narrow set of quality measuremen…
Privacy Policy Enforcement Guardrails for Data-Sensitive Retrieval-Augmented Generation
Osama Zafar, Alexander Nemecek, Yiqian Zhang +5
Standard PII filters often miss contextual data leakage in RAG systems, such as non-regulated attribute clusters that collectively identify individuals. We introduce a Privacy Poli…
CausalGuard: Conformal Inference under Graph Uncertainty
Vikash Singh, Weicong Chen, Debargha Ganguly +12
Estimating treatment effects from observational data requires choosing an adjustment set, but valid adjustment depends on an unknown causal graph. Graph misspecification can cause…
Reliability-Gated Source Anchoring for Continual Test-Time Adaptation
Vikash Singh, Debargha Ganguly, Weicong Chen +8
Continual test-time adaptation (CTTA) updates a pretrained model online on an unlabeled, non-stationary stream while anchoring it to a frozen source checkpoint. This anchor is usef…
AgentCE-Bench: Agent Configurable Evaluation with Scalable Horizons and Controllable Difficulty under Lightweight Environments
Wang Yang, Chaoda Song, Xinpeng Li +7
Existing Agent benchmarks suffer from two critical limitations: high environment interaction overhead (up to 41\% of total evaluation time) and imbalanced task horizon and difficul…
Path-Lock Expert: Separating Reasoning Mode in Hybrid Thinking via Architecture-Level Separation
Shouren Wang, Wang Yang, Chuang Ma +7
Hybrid-thinking language models expose explicit /think and /no_think modes, but current designs do not separate them cleanly. Even in /no_think mode, models often emit long and sel…
Toward Guarantees for Clinical Reasoning in Vision Language Models via Formal Verification
Vikash Singh, Debargha Ganguly, Haotian Yu +5
Vision-language models (VLMs) show promise in drafting radiology reports, yet they frequently suffer from logical inconsistencies, generating diagnostic impressions unsupported by…
Trust The Typical
Debargha Ganguly, Sreehari Sankar, Biyao Zhang +8
Current approaches to LLM safety fundamentally rely on a brittle cat-and-mouse game of identifying and blocking known threats via guardrails. We argue for a fresh approach: robust…
Context Determines Optimal Architecture in Materials Segmentation
Mingjian Lu, Pawan K. Tripathi, Mark Shteyn +4
Segmentation architectures are typically benchmarked on single imaging modalities, obscuring deployment-relevant performance variations: an architecture optimal for one modality ma…
Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level Triggers
Wang Yang, Debargha Ganguly, Xinpeng Li +5
Hybrid reasoning language models are commonly controlled through high-level Think/No-think instructions to regulate reasoning behavior, yet we found that such mode switching is lar…
Efficient Fine-Grained GPU Performance Modeling for Distributed Deep Learning of LLM
Biyao Zhang, Mingkai Zheng, Debargha Ganguly +4
Training Large Language Models(LLMs) is one of the most compute-intensive tasks in high-performance computing. Predicting end-to-end training time for multi-billion parameter model…
LABELING COPILOT: A Deep Research Agent for Automated Data Curation in Computer Vision
Debargha Ganguly, Sumit Kumar, Ishwar Balappanawar +6
Curating high-quality, domain-specific datasets is a major bottleneck for deploying robust vision systems, requiring complex trade-offs between data quality, diversity, and cost wh…
: Online Log Anomaly Detection Via Unsupervised Typicality Learning
Weicong Chen, Vikash Singh, Zahra Rahmani +3
Existing Log Anomaly Detection (LogAD) methods are often slow, dependent on error-prone parsing, and use unrealistic evaluation protocols. We introduce , an unsupervised and p…
Grammars of Formal Uncertainty: When to Trust LLMs in Automated Reasoning Tasks
Debargha Ganguly, Vikash Singh, Sreehari Sankar +7
Large language models (LLMs) show remarkable promise for democratizing automated reasoning by generating formal specifications. However, a fundamental tension exists: LLMs are prob…
Proof of Thought : Neurosymbolic Program Synthesis allows Robust and Interpretable Reasoning
Debargha Ganguly, Srinivasan Iyengar, Vipin Chaudhary +1
Large Language Models (LLMs) have revolutionized natural language processing, yet they struggle with inconsistent reasoning, particularly in novel domains and complex logical seque…
Forte : Finding Outliers with Representation Typicality Estimation
Debargha Ganguly, Warren Morningstar, Andrew Yu +1
Generative models can now produce photorealistic synthetic data which is virtually indistinguishable from the real data used to train it. This is a significant evolution over previ…
Visual Concept Networks: A Graph-Based Approach to Detecting Anomalous Data in Deep Neural Networks
Debargha Ganguly, Debayan Gupta, Vipin Chaudhary
Deep neural networks (DNNs), while increasingly deployed in many applications, struggle with robustness against anomalous and out-of-distribution (OOD) data. Current OOD benchmarks…