Category
3,595 papers
SYNAPSE (Symbolic Neural Alignment for Precise Semantic Extraction for Precise Semantic Extraction) is introduced, a lightweight neuro-symbolic framework that stabilizes neural text generation through inference-time symbolic regularization.
It is shown that inter-layer redundancy can be either localized or globally distributed depending on the LLM architecture, and Representation Locality Score (RLS) is introduced, derived from global inter-layer hidden-state similarity.
Student-Centric Answer Sampling (SCAS) is proposed, a framework that selects from verified teacher-generated answers according to their estimated student-centric learning cost and is derived by a token-wise gradient decomposition and used to guide answer selection during training.
ProMoS is introduced, the first unsupervised generalist GAD framework, which detects anomalies by modeling the abundant normality in unlabeled data, and proposes prototype-guided soft-label distillation to align teacher and student in a shared prototype space, enhancing cross-graph generalizability.
Reach audiences
Advertise in front of researchers, engineers, and readers.
A fixed encoder is studied in a fixed encoder and trajectory reachability metrics (TRM), a small temporal pairwise cost trained from logged trajectories and used to rank predicted endpoints of a candidate action sequence against a goal is introduced.
This research demonstrates that the model, ArchesClimate -- SSP, does not simply imitate scenarios seen during training, but is actually capable of modeling the response of a climate state to diverse forcings, an important step towards reliable and rapid climate model scenario generation.
ProFIL (**Pro**be-**Filtered Reinforcement Learning) is introduced to reduce theater, increase chain-of-thought faithfulness, and shrink chain length in a single, drop-in extension to Group Relative Policy Optimization (GRPO).
This work proposes ADMM-Q, a novel weight quantization algorithm that considers the layer-wise quantization problem, based on a combinatorial variant of the Alternating Direction Method of Multipliers (ADMM).
A dynamic per-layer scalar derived by adapting the LARS/LAMB trust-ratio principle to the orthogonalized setting, where the standard denominator candidates---the raw momentum norm or the polar-factor norm---either live in the wrong unit space or carry no update-scale information.
These results expose a rate-granularity trade-off: PairAlign does not uniformly outperform denser tokenizers on every local metric, but provides a lower-rate symbolic interface preserving ordered and relational structure.
AOPD replaces ineffective negative reinforcement with localized divergence minimization in non-positive advantage regions while preserving positive reinforcement learning and maintains higher policy entropy during training and better capability retention during sequential tool-use adaptation.
The results suggest transformers rotate semantic content into spectrally quiet regions during contextualized processing, where, in some architectures, interventions may reduce grammatical disruption relative to high-variance steering.
Machine Intelligence
A weeklong summer workshop brought higher education faculty to campus to explore how AI and machine learning materials can be adapted for their classrooms.
General Science
Climate & Sustainability
A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.
A new algorithm learns to anticipate the unprecedented scenarios that critical infrastructure and global supply chains are least prepared for.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
