Author

Abu Sa-Adat Mohamed Moon-Im Al Ahsan

6 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Aug 2026

Certified Predictive Value-of-Advice Gating for Cost-Aware Language-Model Guidance in Reinforcement Learning

Language-model advice can accelerate reinforcement learning, but calls are costly and returned actions may be stale or wrong. We formulate advice acquisition as a response-contingent metareasoning problem: before querying, the controller predicts possible parsed responses, evaluates the decision and declared continuati...

Ibne Farabi Shihab, Md Najmus Swaqeeb, Abu Sa-Adat Mohamed Moon-Im Al Ahsan · 0 citations

#machine learning Preprint Aug 2026

Spectral-Guided Diffusion: Accelerating Inference via Static Spectral Layer Scheduling

Diffusion inference repeatedly evaluates the same large network. We ask whether pretrained weights alone can identify residual branches that need not be recomputed throughout the trajectory. Our \textbf{Spectral Concentration Ratio (SCR)} measures leading-versus-tail singular-value energy. Combined with Frobenius magni...

Ibne Farabi Shihab, Abu Sa-Adat Mohamed Moon-Im Al Ahsan, Anuj Sharma · 0 citations

#machine learning Preprint Aug 2026

Spectral Tail Interventions in Decoder-Only Language Models: Reasoning-Sensitive Weight Structure from Controlled Surgery

A finite-width conditional bound linking the inverse participation ratio of squared singular values to central pre-softmax logit kurtosis is derived and a pointwise query--key product-tail target is defined and compared with independent factor surgery with a product-targeted factorization that preserves native attentio...

Ibne Farabi Shihab, Sanjida Akhter, Md Najmus Swaqeeb et al. · 0 citations

Preprint Aug 2026

Finite Constant Frontiers and Auditable Regret Certificates for Average-Reward Reinforcement Learning

Average-reward reinforcement-learning regret is known up to logarithmic factors, but the numerical content of published guarantees is difficult to compare because probability mode, structural parameter, logarithmic normalization, prior information, and planning assumptions differ. We introduce a constant-aware comparis...

Ibne Farabi Shihab, Abu Sa-Adat Mohamed Moon-Im Al Ahsan, Md Najmus Swaqeeb · 0 citations

Preprint Aug 2026

CODS: Iterative Bellman-Residual Data Selection for Reusable Offline Reinforcement Learning

CODS is introduced, a critic-guided selector that alternates between fitting an algorithm-matched critic and acquiring high-residual transitions before freezing a reusable subset, a reusable selection procedure, not a formal coreset guarantee.

Ibne Farabi Shihab, Sanjeda Akter, Abu Sa-Adat Mohamed Moon-Im Al Ahsan et al. · 0 citations

Preprint Aug 2026

Opportunity Is Not Realizability: Selection-Valid Diagnostics for Multi-LLM Routing

The realizable share of oracle opportunity is small and certifiable: strong routers beat the best fixed model, and most of the gap remains, while the selection-valid confidence intervals are small and certifiable.

Ibne Farabi Shihab, Abu Sa-Adat Mohamed Moon-Im Al Ahsan, Md Najmus Swaqeeb · 2 citations