Recommendation & Information Retrieval

Uncovering crucial supporting lemmas for theorem proving by traversing multi-hop dependencies in a formal library's declaration graph.

Simultaneously evaluate $K$ policies in linear contextual bandits with near-optimal sample complexity by sharing information across evaluations via a unified ridge regression estimator.

Multimodal clustering can now adapt to arbitrary instructions, achieving near-perfect V-measures by directly embedding images, text, and instructions.

Most vision-language models fail to correctly bind attributes to objects in complex scenes, but finetuning on synthetic text alone can fix this without harming general performance.

Coding agents fix 40%+ more bugs when they're shown whole files verbatim, not compressed snippets or similar-but-unnecessary code.

A single reward for multiple retrieval actions is a bottleneck; CASI unlocks precise within-set credit assignment, boosting agent performance by 3.51% in production.

Outperforming traditional model selection, a retrieval-based approach finds the best anomaly detector for unseen time series by leveraging similarity to past data, even in challenging OOD scenarios.

LLMs can be steered to generate diverse, relevant responses by explicitly searching for unoccupied semantic "gaps" in their output space, reducing output collision by over 10%.

Weak interactive feedback can dynamically steer LLMs to the correct similarity criterion for test-time decisions, unlocking significant performance gains beyond static mixtures.

AI-powered scoping reviews can now efficiently identify optimal plant trait combinations for ecosystem services, bridging the gap between cutting-edge research and practical application.

Multi-head attention applied to network depth unlocks substantial performance gains and compute efficiency in large MoE models.

Irrelevant text distractors cripple mixed-modality retrieval performance more than images, revealing a text modality preference that degrades performance in a V-shaped curve.

Standard two-level softmax sampling is demonstrably biased; corrected methods achieve near-exact softmax approximations with negligible overhead.

Adversarial shifts in bandit arm means, not just gaps, break standard best-arm identification algorithms, requiring a novel importance-weighting approach for robust performance.

Stored patch vectors from visual document retrieval systems can be inverted to reconstruct original pages, revealing sensitive information and enabling source page identification with high accuracy.

Generative recommender training strategies that append missed targets can actively harm ranking performance by introducing detrimental probability competition.

Black-box MIPS oracles can approximate attention with $O(1/\varepsilon^2)$ keys by augmenting queries and keys, bypassing $\sqrt{n}$ and $\log n$ dependencies.

Intermediate retrieval signals, not just final outcomes, unlock efficient credit assignment for training LLM search agents.

AI agents can now build and reuse persistent, artifact-specific knowledge, dramatically improving their ability to find relevant information for complex tasks and reducing operational costs.

LLMs can learn to actively compute evidence by routing through retrieval and computation, dramatically improving performance on complex, multi-source reasoning tasks.

A single, lightweight model-internal mechanism can effectively bridge the gap between corpus retrieval and long-context inference, outperforming specialized SOTA systems on both.

Personal LLM agents can significantly improve recommendation quality by mediating platform rankings with cross-platform history, but naive mediation introduces substantial harmful overrides.

Sequential recommenders can dramatically boost catalog diversity by adaptively pruning action sets, achieving up to 5.21x diversity gains without sacrificing session depth.

A new benchmark reveals that even sophisticated RAG systems struggle with prompt injection, with DistilBERT leading detection at 89.6% F1.

LLM agents can autonomously optimize RAG pipelines by diagnosing retrieval vs. generation failures, outperforming traditional hyperparameter tuning and achieving Pareto efficiency.

A small, causally identified set of attention heads reliably detects network infrastructure information across diverse LLMs, but their responsibility may reside in single neurons or be distributed across the head depending on the model.

Distributed MMD with Random Fourier Features achieves near-perfect correlation with expected drift magnitude on massive e-commerce data, while per-dimension KS tests falter.

Discover hierarchical cluster structure across multiple scales in directed graphs without knowing the number of clusters beforehand, even across sparse bridges.

A novel cross-domain recommendation framework achieves state-of-the-art book-to-music mood matching by fusing sentiment embeddings with LLM-driven emotional quadrant classification.

A single token can bypass most safety filters, revealing a critical vulnerability in current LLM alignment techniques.

LLM inference cost plummets as a novel output-aware KV cache retrieval method bypasses attention score approximation errors, achieving competitive performance with minimal overhead.

Generative auctions can now achieve externality-aware whole-feed optimization with exact strategyproofness using a transformer, overcoming a critical deployment barrier.

Personalized suicide risk forecasting is significantly improved by embedding patients in a latent space that models similarity, outperforming pooled and per-patient models by up to 30% for first-occurrence event prediction.

NeuroCBIR achieves near-perfect subject re-identification in 3D brain MRIs and encodes clinically relevant information for downstream tasks, all within seconds per scan.

LLM agents will pick a worse item from a "preferred" source over a better item from a "dispreferred" source two-thirds of the time, revealing a critical bias that can be reduced by providing more information.

Monolingual RAG performance significantly improves when the LLM's internal reasoning language is aligned with the query and retrieved documents, even if the model is more proficient in another language.

Relational learning with tabular foundation models can now bypass feature explosion and interaction blindness by propagating information directly through the schema graph.

Expert pairwise rankings, not just absolute scores, can efficiently guide scientific discovery, even when experts have varying fidelity and cost.

Human mobility generation can now be achieved without target trajectories by learning relative movement transitions, not absolute destinations, across cities.

Even advanced LLMs struggle to replicate human researchers' ability to find inspiring prior work, highlighting a significant gap in AI's scientific intuition.

Retrieval pre-training significantly boosts typed decision model performance for biomedical QA, especially when retaining retrieval priors, but its effectiveness hinges critically on the chosen decision head architecture and training objective.

Decision-oriented LLMs like Jev offer a novel quality-latency operating regime for recommendation reranking, outperforming pointwise LLMs in scaling while maintaining strong effectiveness.

LLMs can overcome knowledge gaps in evolutionary search by dynamically co-evolving solutions and targeted web queries, leading to substantial gains in scientific discovery.

A listwise agent inspecting top candidates holistically boosts patch retrieval accuracy by over 27% compared to treating them independently.

Standard information retrieval methods can match LLM-mediated skill selection for agents, slashing per-task costs from $51 to $27.

Parallel search agents can now achieve higher accuracy than generative aggregators by leveraging TRACE to intelligently select the best trajectory from aggregated cross-rollout evidence.

Spherical interpolation between old and new model embeddings recovers backward-compatibility for vision-language retrieval, outperforming orthogonal alignment by finding optimal query directions in the interstitial space.

LLM agents waste immense token budgets repeatedly rediscovering identical cross-document links on every query—pre-indexing corpora into an offline entity-document graph solves fragmented multi-hop retrieval while actually lowering token costs.

Multimodal continual learning does not require rigid parameter isolation or massive replay buffers—external reasoning retrieval can dynamically compose modular capability paths while subspace recycling safely prevents cross-task interference.

Pumping capacity into feature cross-networks yields diminishing returns, but harvesting non-shared estimator variance via recursive weight-sharing unlocks state-of-the-art CTR accuracy without standard ensemble deployment overhead.