Franck Dernoncourt

EDiS: Edge Disjoint Subgraph Sparsification Framework for Graph Neural Networks

Sparse GNN training reduces computation, but deciding which edges to keep can be costly. Reusing one sparse graph is cheap, but locks training to a fixed topology, while varying it across epochs can require repeated sampling or recomputation. We introduce EDiS (Edge-Disjoint Subgraph sparsification framework), which se...

FlexRouter: Learning Complementary Model Sets for Flexible LLM Routing

Existing Large Language Model (LLM) routing methods score LLMs independently to select top-$k$ models. However, this ignores model correlations and enforces a rigid computational budget. Consequently, routers often select redundant models that share failure modes, limiting the overall probability of success. To address...

Controlled Decoding Attacks on Black-Box LLMs

This work introduces \method{}, a framework for jailbreaking through text-only continuation interfaces that permit repeated sampling and assistant-prefix continuation, and achieves the highest mean score most comparisons against baselines.

Reasoning Graph-Structured Question Answering: Datasets and Insights from LLM Benchmarking

Online Learning with LLM Experts from Limited Feedback

We study adaptive routing of prompts to large language model (LLM) experts to maximize response quality in an online setting with limited feedback. We formulate it as a bandit problem with $K$ actions that represent experts and $d$ features that encode prompts, over a horizon of $T$ rounds. We propose algorithms that s...

Beyond Top-$k$ Skill Retrieval: Diversity-Aware Skill Routing for LLM Agents

Diverse Skill Routing is proposed, a diversity-aware reranking framework that uses a Determinantal Point Process to balance relevance and non-redundancy and improves recall and full coverage over a strong pointwise reranking baseline, with larger gains on multi-skill queries.

CRISP: Cliff-awaRe Input-adaptive Sparse Prefilling with Structural-Mass-Motivated Routing

This work replaces the Jensen-Shannon Divergence routing with C_struct, a structural proxy that measures mass at Vertical-Slash compatible positions and reproduces JSD's routing decisions while eliminating both the pooled matmul and subsequent KL divergence overhead.

Not Worth Another Token: Marginal Value Estimation for Efficient Deep Research Agents

The results show that pruning effectiveness depends more on where pruning is applied than on the specific scoring rule: early pruning yields the largest end-to-end savings, while later pruning mainly refines the final synthesis context.

Unifying Graph Neural Networks Through a Common Layer Equation

A common layer equation is introduced that represents covered architectures through seven components: an update domain, channel set, propagation bank, per-channel message maps, channel-fusion operator, ego/residual map, and update map, which exposes the empirical inverse problem of mapping measurable graph and task pro...

Personalized Auto-Research: Towards a True AI Co-Scientist

This work introduces the problem of personalized auto-research, which conditions every stage of the research process on a representation of the individual researcher, and proposes a general and flexible framework that threads a graph-grounded researcher context through retrieval, hypothesis search, experimentation, wri...

GRASP: GRanularity-Aware Search Policy for Agentic RAG

GRASP is introduced, a reinforcement learning (RL) framework for training agents to adaptively coordinate complementary retrieval tools during multi-step reasoning, and it is suggested that learning to coordinate retrieval signals and context granularity is critical for agent's correct reasoning.

Octopus: Gated Selective Attention for Memory-Bounded Long-Context Inference in Large Language Models

O CTOPUS is proposed, a framework that confers fixed-memory inference onto pretrained Transform-ers without the information loss of linearization and outperforms state-of-the-art linearized baselines on the GSM8K benchmark, demonstrating that learned sparse retention serves as an effective regular-izer for long-horizon...