1 citations · 1 across the 34 of their papers we have counts for
26 papers · 1 filter
BLADE: Distilled LLM Regularization for Calibrated Knowledge Graph Completion
Ibne Farabi Shihab, Rabeya Bosri Tamanna, Abdo El Karaky +2
Knowledge graph completion models optimize ranking, although many downstream applications require calibrated probabilities. We present BLADE, a variational model that separates lat…
Task-Aware Spectral Pruning: A Mixture-of-Masks Framework for Efficient LLM Inference
Ibne Farabi Shihab, Fariya Afrin, Sanjeda Akter +1
Static pruning imposes one sparse structure on every prompt, even though reasoning, retrieval, generation, coding, and translation can depend on different parts of a language model…
CODS: Iterative Bellman-Residual Data Selection for Reusable Offline Reinforcement Learning
Ibne Farabi Shihab, Sanjeda Akter, Abu Sa-Adat Mohamed Moon-Im Al Ahsan +2
Offline reinforcement learning repeatedly trains policies from a fixed transition pool, making redundant data costly across seeds and hyperparameters, while naive subsampling can r…
EST-PRM: Stress-Testing Process Reward Models Before They Become Load-Bearing
Ibne Farabi Shihab, Fariya Afrin, Sanjeda Akter +1
Process reward models (PRMs) are widely used in language-model training with dense step-level supervision. They assume PRM scores are stable proxies for step correctness under labe…
Grounded Decoding: Retrieval-Anchored Probability Fusion for Faithful RAG
Ibne Farabi Shihab, Fariya Afrin, Sanjeda Akter +1
As retrieval-augmented generation (RAG) systems scale, it becomes increasingly challenging to ensure faithful grounding in external evidence. Large language models may still priori…
Topology-Aware State Abstraction with Tangle Cores for Markov Decision Processes
Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
State abstraction in reinforcement learning is usually formulated as a partition of states based on reward and transition similarity. This excludes a common structural pattern in n…
Auditing Near-Optimal Policies Can Be Exponentially Hard: Conditional Query Lower Bounds via Occupancy Rashomon Capacity
Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
When many reinforcement-learning policies achieve near-optimal return, a post-hoc auditor may have to distinguish among many behaviorally distinct but return-equivalent policies. W…
Coverage-Based Calibration for Post-Training Quantization via Weighted Set Cover over Outlier Channels
Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
Post-Training Quantization (PTQ) compresses large language models to low bit-widths using a small calibration set, and its quality depends strongly on which samples are chosen. We…
Continual Calibration: Coverage Can Collapse Before Accuracy in Lifelong LLM Fine-Tuning
Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
Continual learning for large language models is typically evaluated through accuracy retention under sequential fine-tuning. We argue that this perspective is incomplete, because u…
Why Colors Make Clustering Harder:Global Integrality Gaps, the Price of Fairness, and Color-Coupled Algorithms in Chromatic Correlation Clustering
Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
Chromatic Correlation Clustering (CCC) extends Correlation Clustering by assigning semantic colors to edges and requiring each cluster to receive a single color label. Unlike stand…
Minimax Optimality and Spectral Routing for Majority-Vote Ensembles under Markov Dependence
Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
Majority-vote ensembles achieve variance reduction by averaging over diverse, approximately independent base learners. When training data exhibits Markov dependence, as in time-ser…
Beyond Accuracy: A Unified Random Matrix Theory Diagnostic Framework for Crash Classification Models
Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
Crash classification models in transportation safety are typically evaluated using accuracy, F1, or AUC, metrics that cannot reveal whether a model is silently overfitting. We intr…
Calibrated Adaptation: Bayesian Stiefel Manifold Priors for Reliable Parameter-Efficient Fine-Tuning
Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
Parameter-efficient fine-tuning methods such as LoRA enable practical adaptation of large language models but provide no principled uncertainty estimates, leading to poorly calibra…
Grassmannian Mixture-of-Experts: Concentration-Controlled Routing on Subspace Manifolds
Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
Mixture-of-Experts models rely on learned routers to assign tokens to experts, yet standard softmax gating provides no principled mechanism to control the tradeoff between sparsity…
On the Sparsifiability of Correlation Clustering: Approximation Guarantees under Edge Sampling
Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
Correlation Clustering (CC) is a fundamental unsupervised learning primitive whose strongest LP-based approximation guarantees require triangle inequality constraints and…
Learning to Forget Attention: Memory Consolidation for Adaptive Compute Reduction
Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
Hybrid architectures combining state-space models with attention have achieved strong efficiency-quality tradeoffs, yet existing approaches either apply attention uniformly or lear…
Certificate-Guided Pruning for Stochastic Lipschitz Optimization
Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
We study black-box optimization of Lipschitz functions under noisy evaluations. Existing adaptive discretization methods implicitly avoid suboptimal regions but do not provide expl…
CalPro: Prior-Aware Evidential--Conformal Prediction with Structure-Aware Guarantees for Protein Structures
Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
Deep protein structure predictors such as AlphaFold provide confidence estimates (e.g., pLDDT) that are often miscalibrated and degrade under distribution shifts across experimenta…
Beyond Variance: Knowledge-Aware LLM Compression via Fisher-Aligned Subspace Diagnostics
Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
Post-training activation compression is essential for deploying Large Language Models (LLMs) on resource-constrained hardware. However, standard methods like Singular Value Decompo…
Anytime-Valid Answer Sufficiency Certificates for LLM Generation via Sequential Information Lift
Sanjeda Akter, Ibne Farabi Shihab, Anuj Sharma
We introduce Sequential-EDFL (Empirical Dynamic Formal Lift), which applies anytime-valid sequential testing to language model generation stopping. Our approach tracks information…
What Fundamental Structure in Reward Functions Enables Efficient Sparse-Reward Learning?
Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
Sparse-reward reinforcement learning (RL) remains fundamentally hard: without structure, any agent needs samples to recover rewards. We introduce…
Selective Risk Certification for LLM Outputs via Information-Lift Statistics: PAC-Bayes, Robustness, and Skeleton Design
Sanjeda Akter, Ibne Farabi Shihab, Anuj Sharma
Large language models often produce confident but incorrect outputs, creating a critical need for reliable uncertainty quantification with formal abstention guarantees. We introduc…
Differentiable Entropy Regularization: A Complexity-Aware Approach for Neural Optimization
Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
We introduce the first differentiable approximation of range-partition entropy, a complexity measure from computational geometry that directly bounds algorithmic runtime. Unlike ar…
Detecting Proxy Gaming in RL and LLM Alignment via Evaluator Stress Tests
Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
Proxy optimization, where AI systems exploit evaluator weaknesses rather than improve intended objectives, threatens both reinforcement learning (reward hacking) and LLM alignment…