Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2605. 14883v2 Announce Type: replace-cross Abstract: Mild traumatic brain injury (mTBI) is a prevalent condition that remains difficult to diagnose in its early stages.
arXiv:2605. 15720v2 Announce Type: replace-cross Abstract: Medical referring image segmentation (MRIS) predicts lesion masks from medical images and natural-language referring expressions, but acquiring paired pixel-level annotations and referring texts is costly.
arXiv:2607. 17082v2 Announce Type: replace-cross Abstract: Large language model agents solve tasks by generating trajectories that interleave planning, tool calls, and intermediate results.
arXiv:2608. 00152v1 Announce Type: new Abstract: Predicting the magnitude of a CRISPRi perturbation's transcriptomic effect on held-out target genes is an important open problem in single-cell biology.
arXiv:2608. 00316v1 Announce Type: new Abstract: Bayesian optimization (BO) has become the standard tool for sample-efficient optimization and owes its efficiency to uncertainty-aware search driven by generic statistical priors.
arXiv:2608. 00106v1 Announce Type: new Abstract: Agentic systems must decide not only what answer to produce, but which reasoning and execution operations should precede it.
arXiv:2608. 00220v1 Announce Type: new Abstract: We show that on-policy reinforcement learning with verifiable rewards (RLVR) can improve the current objective while making successful behaviors for later objectives too rare to sample and reinforce.
arXiv:2608. 00630v1 Announce Type: new Abstract: Achieving continual learning (CL) with deep neural networks requires balancing stability and plasticity while enabling knowledge transfer.
arXiv:2608. 00832v1 Announce Type: new Abstract: Structured plan-generation agents are often evaluated as if a plan has quality in isolation, yet many realistic planning tasks require asking how a candidate behaves when another agent can search for responses.
arXiv:2608. 01205v1 Announce Type: new Abstract: Recent offline reinforcement learning methods increasingly rely on expressive generative policies and specialized value-guidance mechanisms.
arXiv:2608. 01575v1 Announce Type: new Abstract: Whether large language models perform genuine algorithmic reasoning or mere pattern completion is hard to test, because most benchmarks lack a ground truth for correct inductive inference.
arXiv:2608. 01633v1 Announce Type: new Abstract: Large language models (LLMs) enable neural architecture search (NAS) directly over executable neural network programs.
arXiv:2608. 01597v1 Announce Type: new Abstract: Search-augmented LM agents are typically trained with a binary exact-match reward, which throws away most of what a failed trajectory tells us about why it failed.
arXiv:2608. 02222v1 Announce Type: new Abstract: One-shot federated learning (OSFL) has emerged as a promising collaborative model learning framework with only a single round of communication, offering significant advantages in communication efficiency and privacy preservation.
arXiv:2608. 00533v1 Announce Type: cross Abstract: Large Language Models have achieved substantial progress in reasoning capabilities.
arXiv:2606. 19625v2 Announce Type: replace-cross Abstract: We use training-data attribution as an interpretable tool for capability discovery, mapping which regions of the pretraining corpus support social-reasoning versus STEM-reasoning in OLMo3-7B.
arXiv:2608. 01247v1 Announce Type: cross Abstract: Query-agnostic KV cache eviction compresses a context once and reuses the resulting cache for arbitrary future queries, but performance can collapse under tight budgets.
arXiv:2608. 01804v1 Announce Type: new Abstract: Post-training large language models (LLMs) via reinforcement learning (RL) has significantly advanced code generation capabilities.
arXiv:2608. 02139v1 Announce Type: cross Abstract: Large language models (LLMs) capable of self-improvement require not only effective policy optimization, but also a principled mechanism for transforming transient interaction experience into persistent model capabilities.
arXiv:2509. 16577v2 Announce Type: replace Abstract: Over-the-air (OTA) aggregation enables federated edge learning (FEEL) by exploiting the superposition property of the wireless channel to merge communication with computation, eliminating the need to schedule and decode devices individually.